bbuzz_logo_500x500-transparent.png
Schedule
Recordings
bbuzz_logo_500x500-transparent.png
Recordings

Schedule

Join Europe’s leading conference for modern data infrastructure, search and machine learning in Berlin from 7-9 June. We’ll kick of on Sunday with an interactive barcamp followed by two full conference days on Monday and Tuesday!

Schedule

Sunday, 7. June

Sunday
Kesselhaus
Maschinenhaus
Palais Atelier
Frannz Salon
14:30
—
17:30
♥

Barcamp

Palais Atelier
#BBuzz
Nick Burch
14:30 - 17:30 (3h)
Barcamps are informal sessions, a kind of "un-conference", with a schedule decided on the day. It is all driven by the interests and expertise of those who attend so each one is different, but ours are always great!
Add to Calendar (.ics)

Monday, 8. June

Monday
Kesselhaus
Maschinenhaus
Palais Atelier
Frannz Salon
09:30
—
09:35
♥

Opening Session

Kesselhaus
#BBuzz
Paul Berschick
09:30 - 09:35 (5m)
Join us as we kick off Berlin Buzzwords 2026!
Add to Calendar (.ics)
09:35
—
10:20
♥
Operations
People & Community
Society, Ethics & Sustainabilty

Building Resilience: The Next Decade of Open Source

Kesselhaus
Keynote
Ruth Suehle
09:35 - 10:20 (45m)
Over 25 years, open source has become vital digital infrastructure. However, its future relies on human resilience, not just code. To combat burnout, funding gaps, and new regulations, we must move beyond old methods and address sustainability through global policy, security, and community health.
Add to Calendar (.ics)
10:20
—
10:40

Breakfast Break

Kesselhaus
10:20 - 10:40 (20m)

Breakfast Break

Kesselhaus
10:20 - 10:40 (20m)

Breakfast Break

Maschinenhaus
10:20 - 10:40 (20m)

Breakfast Break

Maschinenhaus
10:20 - 10:40 (20m)

Breakfast Break

Palais Atelier
10:20 - 10:40 (20m)

Breakfast Break

Palais Atelier
10:20 - 10:40 (20m)

Breakfast Break

Frannz Salon
10:20 - 10:40 (20m)

Breakfast Break

Frannz Salon
10:20 - 10:40 (20m)
10:40
—
11:00
♥
Data Science
Society, Ethics & Sustainabilty
Stories

Low-Resource Languages as Stress Tests for NLP Data

Kesselhaus
Short Talk
Priscilla Lola Adenuga
10:40 - 11:00 (20m)
Low-resource languages expose weaknesses in NLP systems that are often hidden by benchmark data. Drawing on experience annotating fieldwork data, this talk shows how ambiguity and annotation decisions reveal fundamental data quality issues relevant to real-world NLP pipelines.
Add to Calendar (.ics)
♥
People & Community
Society, Ethics & Sustainabilty

OpenSearch Software Foundation: 1 Year of Open Governance

Maschinenhaus
Short Talk
Kris Freedain, Carlos Rolo
10:40 - 11:00 (20m)
In this presentation, we will talk through moving a major open source project into a foundation and the benefits of open governance, and a vendor-neutral home has proven through a sustained growth in community contributions.
Add to Calendar (.ics)
♥
Data Science
Scale
Search

Relevance Feedback Inside the Search Engine

Palais Atelier
Short Talk
Evgeniya Sukhodolskaya
10:40 - 11:00 (20m)
How does searching for new information often look? Loops: query, review results for relevance, rewrite the query, repeat… Until success, or until the user churns / the token budget burns. This talk introduces a new instrument for search pipeline builders: propagating query-results relevance right inside the search algorithm of a search engine.
Add to Calendar (.ics)
♥
Search
Stories

Towards Chunk-less RAG

Frannz Salon
Short Talk
Carles Onielfa
10:40 - 11:00 (20m)
Retrieval-Augmented Generation (RAG) systems rely on pre-chunked documents, tying retrieval to arbitrary boundaries. This talk explores an experimental approach that surfaces semantically relevant text spans, without chunking. We'll share surprising findings and examine whether this technique points toward a viable chunk-free retrieval paradigm.
Add to Calendar (.ics)
11:10
—
11:50
♥
Stream

Dynamic Broker-Side Filtering for Kafka

Kesselhaus
Talk
David Kjerrumgaard, Álvaro Rodríguez
11:10 - 11:50 (40m)
KAFKA-6020 has been open for 7 years. This talk demos broker-side filtering for Kafka with sub-millisecond latency (p99 < 25ms). Live demo with working code shows how it reduces network costs, simplifies consumers, and enables new use cases. Real-world validation from financial services and logistics deployments.
Add to Calendar (.ics)
♥
Search

Apache Solr 10: What's Coming up for Vector Search

Maschinenhaus
Talk
Alessandro Benedetti, Ilaria Petreti, Anna Ruggero
11:10 - 11:50 (40m)
With Apache Solr 10 out, there are plenty of goodies coming up for vector-search aficionados. From scalar and binary quantization to speed up your search and reduce the memory footprint, to early termination and hybrid approaches to navigate the HNSW graph. Join us if you want to learn about the big steps forward of Apache Solr vector search!
Add to Calendar (.ics)
♥
People & Community
Society, Ethics & Sustainabilty

Mentoring In Open Source in the Age of AI

Palais Atelier
Talk
Tilda Udufo, Busayo Ojo
11:10 - 11:50 (40m)
Open source mentorship changed overnight with AI tools. Contributors submitted polished code they couldn’t explain, making learning harder to assess. This talk shares what we learned mentoring Outreachy contributors—what failed, what worked, and what we’re still figuring out.
Add to Calendar (.ics)
♥
Data Science
Society, Ethics & Sustainabilty
Stories

No 0-day required, just target the AI coding assistant!

Frannz Salon
Talk
Leo Visser
11:10 - 11:50 (40m)
Discover how attackers can manipulate AI coding assistants through hidden text, typosquatting and code errors. Learn to detect concealed instructions and set up trusted dependencies to keep unsafe code out of your environment.
Add to Calendar (.ics)
12:00
—
12:45
♥
Search
Store
Stream

The Agent Era: How AI Agents Are Reshaping Data Platforms

Kesselhaus
Panel
Monica Sarbu, Danica Fine, Philipp Krenn, Till Döhmen
12:00 - 12:45 (45m)
AI agents have quietly become some of the most demanding users of modern data platforms and most weren't built with them in mind. In this panel, leaders from Snowflake, Elastic, MotherDuck, and Xata share what agentic workloads actually look like in production: what broke, what had to be rebuilt, and where the architecture is heading.
Add to Calendar (.ics)
♥
Scale
Search
Stories

Constant-Time Aggregations with Star-Tree in OpenSearch

Maschinenhaus
Talk
Shailesh Kumar Singh
12:00 - 12:40 (40m)
Discover how OpenSearch breaks linear scaling. Inspired by Apache Pinot, the Star-Tree index moves performance dependency from document count to field cardinality. Learn how we extended Lucene’s DocValues to build multi-dimensional materialized views that deliver sub-second analytics on billion-scale datasets for observability workloads.
Add to Calendar (.ics)
♥
Operations
Scale
Stream

Beyond the Hype: When Apache Flink Solves Real Problems

Palais Atelier
Talk
Naci Simsek
12:00 - 12:40 (40m)
When does Apache Flink solve real problems versus add complexity? Explore use cases where Flink becomes essential such as fraud detection, CDC, real-time analytics versus when batch or Kafka Streams suffice. Compare stream engines (Flink, Spark) with platforms (Kafka, Pulsar) to confidently decide when streaming delivers value.
Add to Calendar (.ics)
♥
People & Community
Search

OSS Security: Lessons from 10+ Years at Apache Solr

Frannz Salon
Talk
Jason Gerlowski
12:00 - 12:40 (40m)
How are security decisions big and small made in a distributed open source community? Come find out at this session where users will gain insights and examples (both good and bad) to take back to their own projects.
Add to Calendar (.ics)
12:40
—
14:00
Continuing until 12:45: The Agent Era: How AI Agents Are Reshaping Data Platforms

Lunch Break

Maschinenhaus
12:40 - 14:00 (1h 20m)

Lunch Break

Maschinenhaus
12:40 - 14:00 (1h 20m)

Lunch Break

Palais Atelier
12:40 - 14:00 (1h 20m)

Lunch Break

Palais Atelier
12:40 - 14:00 (1h 20m)

Lunch Break

Frannz Salon
12:40 - 14:00 (1h 20m)

Lunch Break

Frannz Salon
12:40 - 14:00 (1h 20m)
12:45
—
14:00
Continuing until 14:00: Lunch Break
Continuing until 14:00: Lunch Break
Continuing until 14:00: Lunch Break
Continuing until 14:00: Lunch Break
14:00
—
14:40
♥
Scale
Search

Agentic Retrieval: Building Self-Optimizing Search Systems

Kesselhaus
Talk
Jo Kristian Bergum
14:00 - 14:40 (40m)
Relevance feedback loops used to take months. AI agents can now compress the process to seconds. This talk explores agentic retrieval: systems where agents adjust scoring models, schema, and indexing in real time. Learn how to build retrieval infrastructure with verifiable APIs that enable agents to optimize their own search context.
Add to Calendar (.ics)
♥
Scale
Store
Stream

Turning the database inside out again

Maschinenhaus
Talk
Tom Scott, Roman Kolesnev
14:00 - 14:40 (40m)
We rethink data systems by putting streams at the center. Expanding on Martin Kleppmann's: Turning the Database Inside Out, this talk shows how Apache Kafka and Apache Iceberg together provide durable storage, indexing, and rich views that eliminate brittle ETL and unify real-time and historical analysis. A new way to see databases—and streams.
Add to Calendar (.ics)
♥
Data Science
Operations
Stream

Apache Spark Declarative Pipelines in Action

Palais Atelier
Talk
Frank Munz
14:00 - 14:40 (40m)
Learn Spark 4.1's brand-new Declarative Pipelines, a paradigm shift replacing imperative code with simple declarations. We'll build a real-time data pipeline together, processing streaming ADS-B flight data from tens of thousands of aircraft overhead.
Add to Calendar (.ics)
♥
Store

Herding Cat(alogue)s: The Apache Iceberg™ Catalog Landscape

Frannz Salon
Talk
Danica Fine
14:00 - 14:40 (40m)
Apache Iceberg™ relies on catalogs, but with many options available, choosing the right one is challenging. This session explores the Iceberg catalog landscape, covering core functions, the impact of REST catalogs, and comparisons of Hive, JDBC, Snowflake, and Apache Polaris™ to help you select the best fit for your needs.
Add to Calendar (.ics)
14:50
—
15:10
♥
Data Science
Store
Stories

Ultraviolet: Turn Hidden Document Data into an AI Advantage

Kesselhaus
Short Talk
Alessio Vertemati
14:50 - 15:10 (20m)
Every PDF hides a world of structure, metadata and embedded signals that can silently influence AI based processing. With ultraviolets, we reveal how those can be exploited for malicious purposes and even become powerful tools for smarter applications. Designing for both humans and machines become a vital aspect of AI experience design.
Add to Calendar (.ics)
♥
Scale
Search
Store

From OLTP to OLAP: Is PostgreSQL Eating Analytics Too?

Maschinenhaus
Short Talk
Daniel Seybold
14:50 - 15:10 (20m)
Can PostgreSQL become a serious analytics engine? With emerging columnar extensions, PostgreSQL is pushing beyond OLTP into OLAP territory. This talk explores the current columnar landscape, architectural trade-offs, and how far PostgreSQL can go compared to analytical engines like ClickHouse.
Add to Calendar (.ics)
♥
Data Science
Scale
Search

Tensor arithmetics in search and ranking for Ecommerce.

Palais Atelier
Short Talk
Piotr Kobziakowski
14:50 - 15:10 (20m)
Small, domain-specific vision models can dramatically enhance the buyer search experience by delivering more relevant visual understanding. But the real opportunity comes from controllable image embeddings: by fusing base search embeddings with additional control vectors, representing features such as color, shape, and style,
Add to Calendar (.ics)
♥
Data Science
Society, Ethics & Sustainabilty
Store

Scientific Data Under Threat in Today’s America

Frannz Salon
Short Talk
Uwe Schindler
14:50 - 15:10 (20m)
A brief look at how scientific data came under political pressure during the presidency of Donald Trump, and how scientists and data repositories in Europe worked to protect public access to evidence-based research, ensuring access for data science in a well-structured way.
Add to Calendar (.ics)
15:20
—
16:00
♥
Operations
Scale
Store

How Apache Iceberg Enables Multi-Engine Data Platforms

Kesselhaus
Talk
Geetha Anne
15:20 - 16:00 (40m)
the session will cover operational best practices, including metadata management, file sizing, compaction strategies, and performance tuning at scale. Attendees will leave with practical guidance for designing &operating open, flexible, multi-engine data architectures built on Apache Iceberg, enabling faster analytics, lower operational flexibility
Add to Calendar (.ics)
♥
Operations
Stories
Stream

Streamling: Lightweight, Extensible Streaming on DataFusion

Maschinenhaus
Talk
Xiao Meng, Rafael Aguiar
15:20 - 16:00 (40m)
Apache DataFusion is moving beyond batch into streaming. We built Streamling, a Rust streaming engine that uses DataFusion planning and Arrow RecordBatch streams for real-time SQL/WASM transforms. This talk covers how we built it, highlights key features (FFI plugins, WASM transforms, and dynamic tables), and shares production lessons.
Add to Calendar (.ics)
♥
Data Science
Scale
Store

Why Choose One: Multi-Engine Analytics with Apache Wayang

Palais Atelier
Talk
Zoi Kaoudi, Haralampos Gavriilidis
15:20 - 16:00 (40m)
Choosing the best engine for each data task sounds right, but in modern data stacks doing so requires expertise and effort. Apache Wayang, a recently graduated TLP, addresses this by decoupling logical dataflows from execution engines. From big data platforms to SQL and ML engines, Wayang enables cross-platform execution that maximizes performance.
Add to Calendar (.ics)
♥
Data Science
Stories

Let LLMs Wander: Engineering RL Environments

Frannz Salon
Talk
Stefano Fiorucci
15:20 - 16:00 (40m)
What if, instead of learning only from examples, Language Models could explore crafted Environments, little worlds where they can act and improve autonomously? Join me to see how Reinforcement Learning Environments work, how to build them with open-source tools, and how to use them to evaluate and train LLMs/Agents.
Add to Calendar (.ics)
16:00
—
16:30

Coffee Break

Kesselhaus
16:00 - 16:30 (30m)

Coffee Break

Kesselhaus
16:00 - 16:30 (30m)

Coffee Break

Maschinenhaus
16:00 - 16:30 (30m)

Coffee Break

Maschinenhaus
16:00 - 16:30 (30m)

Coffee Break

Palais Atelier
16:00 - 16:30 (30m)

Coffee Break

Palais Atelier
16:00 - 16:30 (30m)

Coffee Break

Frannz Salon
16:00 - 16:30 (30m)

Coffee Break

Frannz Salon
16:00 - 16:30 (30m)
16:30
—
17:10
♥
Operations
Store
Stories

10x CouchDB Performance Gains for a AAA Game Launch

Kesselhaus
Talk
Jan Lehnardt
16:30 - 17:10 (40m)
All software benchmarks and claims of performance are carefully crafted lies and this talk is no different. Instead of giving you a quick “do steps one, two, three for a magic speedup”, we aim to explain how we arrived at the changes we made and how we rigorously tested those changes to make sure we understand their impact.
Add to Calendar (.ics)
♥
Data Science
Search
Store

Search is Back: Solving the "Context Crisis" for AI Agents

Maschinenhaus
Talk
David Louis Hollembaek, Vincent Pistor
16:30 - 17:10 (40m)
Why do smart agents make dumb mistakes? The culprit is context, an old problem with new solutions. Let's fast-forward through 20 years of search evolution to fix the missing link in today’s Agentic AI. We’ll demonstrate how to combine Knowledge Graphs and Vector Search to build reliable, context-aware applications using open-source tools.
Add to Calendar (.ics)
♥
Operations
Scale
Stream

Event-driven Agents with Complex Event Processing in Flink

Palais Atelier
Talk
Steffen Hoellinger
16:30 - 17:10 (40m)
Event-driven Agents calling LLMs can be combined with Pattern Recognition and Anomaly Detection in Apache Flink in smart ways to increase cost efficiency, avoid hallucinations and enforce predictable, deterministic behavior. Specifically in a business process context, this architecture provides opportunities for continuous real-time process mining.
Add to Calendar (.ics)
♥
Operations
Scale
Society, Ethics & Sustainabilty

SPRUCE it up! Open Source GreenOps at scale

Frannz Salon
Talk
Julien Nioche
16:30 - 17:10 (40m)
GreenOps adoption is stalled by missing data from cloud providers. SPRUCE is an open-source, scalable platform built on Apache Spark that enriches cloud usage reports with open models to quantify carbon impact, build insights, and help teams reduce both emissions and cloud spend.
Add to Calendar (.ics)
17:20
—
18:05
♥
Search

AI is here – time to throw away our search engines?

Kesselhaus
Panel
Charlie Hull, Atita Arora, Jo Kristian Bergum, Dmitry Kan, Evgeniya Sukhodolskaya
17:20 - 18:05 (45m)
Why do we even need traditional search when AI can do everything? Or is it foolish to ignore simple, proven techniques for delivering great results? What's the best way to combine old and new? Join our panel of experts for a fun and provocative debate!
Add to Calendar (.ics)
♥
Data Science
Search
Stories

Building a Local News RAG: The Quest for Trustworthiness

Maschinenhaus
Talk
Marcel Dokters
17:20 - 18:00 (40m)
We will show you how we build a local newspaper rag and all the problems that came along the way. From trustworthiness to customer wishes, search optimization and generation problems. Local villages, that LLMs know nothing about, content that is semantically the same and outdated information are only a part of the journey we made.
Add to Calendar (.ics)
♥
Operations
Scale
Store

Floe: Policy-Based Table Maintenance for Apache Iceberg

Palais Atelier
Talk
Neelesh Salian
17:20 - 18:00 (40m)
Iceberg maintenance procedures work. Orchestrating them across hundreds of tables is the problem. Floe is an open-source system that treats maintenance as policy: glob patterns, schedules, and health-driven triggers that gate operations on real table metrics. Supports 7 catalogs, executes via Spark or Trino.
Add to Calendar (.ics)
♥
Data Science
Operations

Observability’s Sixth Sense: Detecting Anomalies in Metrics

Frannz Salon
Talk
Diana Todea
17:20 - 18:00 (40m)
In this talk, we look at anomaly detection as a complementary way of working with metrics. Instead of relying on predefined limits, anomaly detection focuses on identifying behavior that deviates from what is normally observed over time. The focus is on how developers can interpret these signals, where anomaly detection is useful, where it is not.
Add to Calendar (.ics)
18:05
—
21:05
♥

Get-Together

Kesselhaus
#BBuzz
18:05 - 21:05 (3h)
Join us for food and drinks at Palais Kulturbrauerei!
Add to Calendar (.ics)

Tuesday, 9. June

Tuesday
Kesselhaus
Maschinenhaus
Palais Atelier
Frannz Salon
09:30
—
09:50
♥
Search

Reviving phonetic algorithms for better search relevance

Kesselhaus
Short Talk
Pietro Mele, Radu Pop
09:30 - 09:50 (20m)
Fuzzy search is a double-edged sword: it fixes typos but drowns users in noise on large corpora. At INA, we revived ancient phonetic algorithms to improve relevance. This session compares fuzzy vs. phonetic search on a massive archive, showing how "sounding right" beats "spelling close."
Add to Calendar (.ics)
♥
Data Science
Search

Circular Dependency Fixes when Bootstrapping a Golden Set

Maschinenhaus
Short Talk
Radu Gheorghe, Rafał Kuć
09:30 - 09:50 (20m)
For a golden set, you need queries. Even if you have them, you can’t judge all docs for each query. Only the top N. How do we rank the top N? See the circular dependency? We’ll talk about ways to untangle it: lexical search, significant terms, training an embedder from scratch, etc. By iteratively refining data and queries, we'll get there.
Add to Calendar (.ics)
♥
Search

Personalize Search Results with OpenSearch Agentic Memory

Palais Atelier
Short Talk
Hajer Bouafif
09:30 - 09:50 (20m)
Improving search relevance typically requires complex personalization pipelines — recommendation engines, feature stores, ML models. This session shows a simpler path: multiple lightweight agents that collaborate through OpenSearch's agentic memory to understand and enrich queries in real time. Same query, different results for different users.
Add to Calendar (.ics)
♥
Data Science
Scale
Store

Writes, 3 ways: Postgres, Apache Kafka® and Apache Iceberg™

Frannz Salon
Short Talk
Celeste Horgan
09:30 - 09:50 (20m)
Learning new things is hard, but a useful way to think about new things is by comparing them to things you already know. In this talk, we'll compare writes between 3 different popular data services: Postgres, Apache Kafka and Apache Iceberg. In doing so, we'll learn a bit about the evolution of how we've thought of data storage as developers.
Add to Calendar (.ics)
10:00
—
10:40
♥
Scale
Search
Stream

From Inverted Index to Columnar Vectorized Execution Search

Kesselhaus
Talk
Ankit Jain
10:00 - 10:40 (40m)
Search engines are converging with analytical data systems. This talk explores how columnar data layouts, SIMD-accelerated execution, and bulk-oriented processing are reshaping search internals. We examine where traditional models fall short and how hardware-aware techniques from analytics engines are defining the next search infrastructure.
Add to Calendar (.ics)
♥
Data Science
Search

Text-to-Struct: Fine-tuning SLMs for Query Intent

Maschinenhaus
Talk
Hugo Jimenez, Sandra Bullón
10:00 - 10:40 (40m)
Hybrid search fails on complex intent: vector search misses constraints, keywords miss nuance. This talk explores fine-tuning SLMs for 'Query Understanding'—transforming vague inputs into structured requests. Learn to extract metadata, expand terms, and route intent to build a search engine that does the hard work for your users.
Add to Calendar (.ics)
♥
Data Science
Store
Stream

Kafi Streams: Complex Stream Processing Made Simple

Palais Atelier
Talk
Ralph Matthias Debusmann
10:00 - 10:40 (40m)
You can finally stop caring about co-partitioning, state stores and eventual consistency. Kafi Streams, built on (Py)DBSP, treats streaming like batch — strongly consistent, no special concepts. An Open Source Python library for the 80% of use cases that don't need extreme scale. Fully incremental stream processing for everyone, from day one.
Add to Calendar (.ics)
♥
Operations
Scale

GitOps for n8n: Treating Workflows as Code

Frannz Salon
Talk
Joao Gilberto Magalhaes
10:00 - 10:40 (40m)
n8n-gitops is an open-source CLI that applies GitOps principles to n8n workflows. This talk shows how workflows can be exported, reviewed, versioned, and deployed from Git instead of manually promoted via the UI. Through a live demo, we explore safer deployments, rollbacks, and lessons learned operating automation as code.
Add to Calendar (.ics)
10:40
—
11:10

Breakfast Break

Kesselhaus
10:40 - 11:10 (30m)

Breakfast Break

Kesselhaus
10:40 - 11:10 (30m)

Breakfast Break

Maschinenhaus
10:40 - 11:10 (30m)

Breakfast Break

Maschinenhaus
10:40 - 11:10 (30m)

Breakfast Break

Palais Atelier
10:40 - 11:10 (30m)

Breakfast Break

Palais Atelier
10:40 - 11:10 (30m)

Breakfast Break

Frannz Salon
10:40 - 11:10 (30m)

Breakfast Break

Frannz Salon
10:40 - 11:10 (30m)
11:10
—
11:50
♥
Data Science
Search
Stories

When better retrieval makes agents worse

Kesselhaus
Talk
Lester Solbakken
11:10 - 11:50 (40m)
Agentic systems can break not because information is missing, but because persuasively wrong context gets promoted into action. We examine a recurring pattern: retrieval metrics improve while agent behavior degrades as distractors enter multi-step loops. We show why relevance, reliability, and security are tightly connected in agentic retrieval.
Add to Calendar (.ics)
♥
Scale
Search

Context-Aware Segments: Solving the "Scatter-Read" Problem

Maschinenhaus
Talk
Rishav Sagar, Tejas Shah
11:10 - 11:50 (40m)
Traditional OpenSearch segments are context-blind, scattering data across multiple segments. We introduce Context-Aware Segments (CAS), an architecture that brings "sharding" logic to the segment level. By enforcing document locality during indexing, we slashed query latency and minimized data footprint through superior pruning and compression.
Add to Calendar (.ics)
♥
Store

DuckDB beyond the notebook

Palais Atelier
Talk
Matthias Niehoff
11:10 - 11:50 (40m)
Most people know DuckDB as a fast analytics tool for notebooks and scripts. But embedded OLAP enables much more: browser-based analytics via WebAssembly, serverless data processing, and lightweight data apps — without heavy infrastructure. This talk shows how DuckDB changes the way we build data-driven applications.
Add to Calendar (.ics)
♥
Data Science
Search
Stream

Real-Time ML Pipelines: Feature Chaining with Chronon

Frannz Salon
Talk
Varant Zanoyan
11:10 - 11:50 (40m)
Modern ML applications demand features computed in near real-time with sub-100ms latencies. This talk dives into Chronon, an OSS feature platform bridging streaming data infrastructure and production ML. Using a two-tower search pipeline example, we'll show how we can chain embeddings with tabular features while minimizing hot-path computation.
Add to Calendar (.ics)
12:00
—
12:40
♥
Operations
Store
Stream

Keeping data private in real-time pipelines

Kesselhaus
Talk
Olena Kutsenko
12:00 - 12:40 (40m)
Real-time data is awesome… until you realize it’s leaking names, emails, and locations. In this talk, you’ll learn how to keep streaming data private, from simple masking to tricks that beat re-identification. All with live demos and some juicy real-world stories.
Add to Calendar (.ics)
♥
Scale
Search
Store

C++ Search for Database Kernels: Built In, Not Bolted On

Maschinenhaus
Talk
Andrey Abramov
12:00 - 12:40 (40m)
IResearch is an Apache 2.0 C++ search engine built to live inside databases. We'll benchmark it against leading open-source search engines, show why vectorized scoring is the next frontier for information retrieval engines, share the mistakes we made over a decade of development and explore how database-native search fits modern query execution.
Add to Calendar (.ics)
♥
Operations
Scale
Society, Ethics & Sustainabilty

Escaping the Cloud: High-Performance AI in your Browser

Palais Atelier
Talk
Johannes Kolbe
12:00 - 12:40 (40m)
Server-side inference is the bottleneck of modern AI, creating costs and privacy hurdles. But what if the solution is scaling down to the browser? This session investigates Client-Side AI using WebGPU, ONNX Runtime, and Transformers.js. We’ll explore the reality of hardware access, model size, and the 2026 trade-offs of browser based execution.
Add to Calendar (.ics)
♥
Data Science
Operations

The Failures That Don't Crash: MLOps for AI Agents

Frannz Salon
Talk
Bartosz Mikulski
12:00 - 12:40 (40m)
This talk takes four reliability patterns from distributed systems and shows what they look like inside an agent architecture. How to shadow-test an agent. Why your circuit breakers need confidence thresholds. What an eval harness looks like when your system is non-deterministic. And why human oversight degrades faster than anyone admits.
Add to Calendar (.ics)
12:40
—
14:00

Lunch Break

Kesselhaus
12:40 - 14:00 (1h 20m)

Lunch Break

Kesselhaus
12:40 - 14:00 (1h 20m)

Lunch Break

Maschinenhaus
12:40 - 14:00 (1h 20m)

Lunch Break

Maschinenhaus
12:40 - 14:00 (1h 20m)

Lunch Break

Palais Atelier
12:40 - 14:00 (1h 20m)

Lunch Break

Palais Atelier
12:40 - 14:00 (1h 20m)

Lunch Break

Frannz Salon
12:40 - 14:00 (1h 20m)

Lunch Break

Frannz Salon
12:40 - 14:00 (1h 20m)
14:00
—
14:40
♥
Search
Stream

The Three-Body Problem of Inverse Hybrid Search

Kesselhaus
Talk
Ravindra Harige
14:00 - 14:40 (40m)
When users expect alerts for new products matching an uploaded image, the problem becomes inverse hybrid search. Unlike top-K search, alerting must guarantee fetch-all semantics: zero missed matches across all saved searches, combining vector similarity, boolean filters, and lexical signals. We show why this breaks traditional scaling intuition.
Add to Calendar (.ics)
♥
Scale
Search
Stories

One GPU, Four Retrieval Modes: Multi-Model Search Serving

Maschinenhaus
Talk
Filip Makraduli
14:00 - 14:40 (40m)
Competitive search now needs dense embeddings, sparse vectors, ColBERT, and cross-encoder reranking. Most teams run four separate containers. This talk shows how to serve all four from one process, walks through building a hybrid retrieval pipeline with real benchmark data, and covers where each retrieval mode wins and where it wastes compute.
Add to Calendar (.ics)
♥
Scale
Stream

What If We've Been Scaling Stream Processing Wrong All Along

Palais Atelier
Talk
Hartmut Armbruster
14:00 - 14:40 (40m)
We’ve normalised extraordinary inefficiency in stream processing. Thousands of events/sec don't justify repartition storms, serialization overhead, state migration. This talk explores a different path: Kafka Streams DSL, adopt Flink-like exactly-once semantics, Project Loom, and challenging the assumption that stream processing must be distributed.
Add to Calendar (.ics)
♥
Data Science
Operations
Stories

How to Tell If Your Agent Used the Right Stuff

Frannz Salon
Talk
Apurva Misra
14:00 - 14:40 (40m)
Many so-called “agent failures” are actually context failures in disguise. In this session, we’ll explore how to tell whether your agent truly saw and used the right context, using techniques like tracing and attribution, golden datasets for context-aware evaluation, and targeted probes to test retrieval quality.
Add to Calendar (.ics)
14:50
—
15:30
♥
Scale
Search

Beyond Grep: Search for Reliable Coding Agents

Kesselhaus
Talk
Amine GANI, Roudy Khoury
14:50 - 15:30 (40m)
Coding agents succeed in verifiable loops (compiler + tests), but large repos still expose retrieval weaknesses. This session explores how lexical, structural, and semantic search can provide cleaner context for LLMs. We compare tradeoffs and evaluation approaches to improve reliability without inflating token cost.
Add to Calendar (.ics)
♥
Search
Stories

Zero downtime index upgrade in Apache Solr

Maschinenhaus
Talk
Rahul Goswami
14:50 - 15:30 (40m)
In this talk we'll explore how Apache Solr introduced the capability to upgrade an index in-place with zero downtime. This upgrade path helps prepare the index for a future Solr major version upgrade without needing to recreate the index from source as is the case with Lucene based search engines today.
Add to Calendar (.ics)
♥
Data Science

Detecting Hidden Bias in Datasets Before Models Fail

Palais Atelier
Talk
Stas Don
14:50 - 15:30 (40m)
Hidden bias in datasets silently breaks machine learning systems in production. This talk shows how to detect data imbalance, leakage, and coverage gaps early using practical metrics, visualizations, and open-source tools—before misleading offline metrics turn into costly real-world failures.
Add to Calendar (.ics)
♥
Data Science
Operations
Scale

Sunset for the Wild West: Making ML disciplined by default

Frannz Salon
Talk
William Benton
14:50 - 15:30 (40m)
Many novel machine learning techniques started as clever hacks that just happened to work, but the demands of building real systems can be at odds with this creative culture. Learn about our open-source stack to improve quality-of-life for ML researchers and infrastructure teams alike — and how their concerns aren't as different as you might think.
Add to Calendar (.ics)
15:30
—
16:00

Coffee Break

Kesselhaus
15:30 - 16:00 (30m)

Coffee Break

Kesselhaus
15:30 - 16:00 (30m)

Coffee Break

Maschinenhaus
15:30 - 16:00 (30m)

Coffee Break

Maschinenhaus
15:30 - 16:00 (30m)

Coffee Break

Palais Atelier
15:30 - 16:00 (30m)

Coffee Break

Palais Atelier
15:30 - 16:00 (30m)

Coffee Break

Frannz Salon
15:30 - 16:00 (30m)

Coffee Break

Frannz Salon
15:30 - 16:00 (30m)
16:00
—
16:40
♥
Operations

Correctness Too Cheap To Meter: Formal Verification and LLMs

Kesselhaus
Talk
Emilie Ma
16:00 - 16:40 (40m)
Formal methods are powerful tools to verify software systems' correctness and reliability. However, manually writing system specs is time-consuming and hard to maintain. LLMs can help with this burden. We'll share new research into tools to automate formal methods workflows and learnings from how LLMs currently perform.
Add to Calendar (.ics)
♥
Operations
People & Community
Society, Ethics & Sustainabilty

Empowering OSS maintainers in the age of AI

Maschinenhaus
Talk
Jarek Potiuk
16:00 - 16:40 (40m)
This talk addresses how we attempt to manage the changes to Open Source Maintainership resulting from the Agentic AI approach within the Apache Software Foundation. The Apache Way is About People — AI should free maintainers to do stuff that matters, not replace them; it should empower maintainers in the Age of AI.
Add to Calendar (.ics)
♥
Operations
Store

What you should know about constraints in PostgreSQL 18

Palais Atelier
Talk
Gülçin Yıldırım Jelinek
16:00 - 16:40 (40m)
This talk explains how constraints work in Postgres by exploring the pg_constraint catalog and core concepts like table vs. column constraints, constraint triggers, domains and constraint deferrability through SQL queries. It then covers what’s new in Postgres 18 including temporal keys, NOT NULL as a first-class constraint, NOT ENFORCED and more.
Add to Calendar (.ics)
16:50
—
17:10
♥
Data Science
Scale
Search

From Legacy Search to Vespa: What a Real PoC Taught Us

Kesselhaus
Short Talk
André Charton, Valeriia Platonova
16:50 - 17:10 (20m)
For years, Germany’s largest classifieds website relied on a search-first relevance approach because structured data was sparse. This talk shares how we introduced Vespa in the Motors category, enriched signals with embeddings and extracted attributes, and migrated step by step; what worked, what failed, and which lessons only a real PoC reveals.
Add to Calendar (.ics)
♥
People & Community
Search

How to Survive the Vortex of LLM Change

Maschinenhaus
Short Talk
Carmen Iniesta, Carles Onielfa
16:50 - 17:10 (20m)
The LLM ecosystem changes faster than most teams can adapt. This talk shares our experience and the practical lessons we’ve learned while building an intelligent search product in a world where models, tools, and best practices constantly evolve.
Add to Calendar (.ics)
♥
Data Science
People & Community
Stories

AI in the physical world: from observation to discovery

Palais Atelier
Short Talk
Dmitriy Kostunin, Julian von Hoerschelmann-Schliwinski
16:50 - 17:10 (20m)
In 2026, AI is moving beyond digital tasks into the physical world. It increasingly interacts with instruments, experiments, and real-world data. Physicists stand at this frontier, using deep learning, LLMs, and agents to analyze nature itself. What have we learned about AI when it meets reality?
Add to Calendar (.ics)
17:10
—
17:20
♥

Closing Session

Kesselhaus
#BBuzz
Paul Berschick
17:10 - 17:20 (10m)
Join us as we wrap up Berlin Buzzwords.
Add to Calendar (.ics)

Like what you see?

A talking letter B with legs

You like our program? Get your ticket now!

Skip to content