talk-data.com

At Berlin Buzzwords, industry voices highlighted how search is evolving with AI and LLMs.

• Kacper Łukawski (Qdrant) stressed hybrid search (semantic + keyword) as core for RAG systems and promoted efficient embedding models for smaller-scale use.
• Manish Gill (ClickHouse) discussed auto-scaling OLAP databases on Kubernetes, combining infrastructure and database knowledge.
• André Charton (Kleinanzeigen) reflected on scaling search for millions of classifieds, moving from Solr/Elasticsearch toward vector search, while returning to a hands-on technical role.
• Filip Makraduli (Superlinked) introduced a vector-first framework that fuses multiple encoders into one representation for nuanced e-commerce and recommendation search.
• Brian Goldin (Voyager Search) emphasized spatial context in retrieval, combining geospatial data with AI enrichment to add the “where” to search.
• Atita Arora (Voyager Search) highlighted geospatial AI models, the renewed importance of retrieval in RAG, and the cautious but promising rise of AI agents.

Together, their perspectives show a common thread: search is regaining center stage in AI—scaling, hybridization, multimodality, and domain-specific enrichment are shaping the next generation of retrieval systems.

Kacper Łukawski Senior Developer Advocate at Qdrant, he educates users on vector and hybrid search. He highlighted Qdrant’s support for dense and sparse vectors, the role of search with LLMs, and his interest in cost-effective models like static embeddings for smaller companies and edge apps. Connect: https://www.linkedin.com/in/kacperlukawski/

Manish Gill
Engineering Manager at ClickHouse, he spoke about running ClickHouse on Kubernetes, tackling auto-scaling and stateful sets. His team focuses on making ClickHouse scale automatically in the cloud. He credited its speed to careful engineering and reflected on the shift from IC to manager.
Connect: https://www.linkedin.com/in/manishgill/

André Charton
Head of Search at Kleinanzeigen, he discussed shaping the company’s search tech—moving from Solr to Elasticsearch and now vector search with Vespa. Kleinanzeigen handles 60M items, 1M new listings daily, and 50k requests/sec. André explained his career shift back to hands-on engineering.
Connect: https://www.linkedin.com/in/andrecharton/

Filip Makraduli
Founding ML DevRel engineer at Superlinked, an open-source framework for AI search and recommendations. Its vector-first approach fuses multiple encoders (text, images, structured fields) into composite vectors for single-shot retrieval. His Berlin Buzzwords demo showed e-commerce search with natural-language queries and filters.
Connect: https://www.linkedin.com/in/filipmakraduli/

Brian Goldin
Founder and CEO of Voyager Search, which began with geospatial search and expanded into documents and metadata enrichment. Voyager indexes spatial data and enriches pipelines with NLP, OCR, and AI models to detect entities like oil spills or windmills. He stressed adding spatial context (“the where”) as critical for search and highlighted Voyager’s 12 years of enterprise experience.
Connect: https://www.linkedin.com/in/brian-goldin-04170a1/

Atita Arora
Director of AI at Voyager Search, with nearly 20 years in retrieval systems, now focused on geospatial AI for Earth observation data. At Berlin Buzzwords she hosted sessions, attended talks on Lucene, GPUs, and Solr, and emphasized retrieval quality in RAG systems. She is cautiously optimistic about AI agents and values the event as both learning hub and professional reunion.
Connect: https://www.linkedin.com/in/atitaarora/

Venue: 1 Angel Lane, EC4R 3AB

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. You MUST use your full real names on your meetup profile, otherwise, you will NOT make it on the guest list! 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event.

If your RSVP status says "You're going" you will be able to get in. No further confirmation required. You will NOT need to show your RSVP confirmation when signing in.

If you can no longer make it, please unRSVP as soon as you know so we can assign your place to someone on the waiting list.

Code of Conduct: This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct.

As always, there'll be free food & drinks, generously provided by our host, Man Group.

Main Talks 1️⃣ Simplifying Real-Time ML Pipelines with Quix Streams - Tomas Neubauer

As data volume and velocity continue to increase, the need for real-time machine learning (ML) is becoming more pressing. However, building real-time ML pipelines can be complex and time-consuming, requiring expertise in both ML and streaming application development. This talk will address this problem by introducing Quix Streams, an open-source Python library that makes it easy for data scientists and ML engineers to build real-time ML pipelines without having to learn the intricacies of building a streaming application from scratch.

2️⃣ Transformers Inside Out - Sam Joseph

Large Language Models like GPT4 have catapulted transformers into the limelight, but how do they really work? How can you really code them? This talk presents a new set of flow diagrams that more closely match the code in order to better understand transformers inside out!

Lightning Talks ⚡ ⚡1️⃣ Python in Excel - Mark Rotchell

A high level overview of the recent announcement of Python integration into Excel - what it looks like to have Python in a spreadsheet, why you might want to use it, and why I think it's a good thing for the Python community.

⚡2️⃣ Sometimes the music and playlists we hear don't hit our mood we are feeling, can AI help with this ? - Filip Makraduli

An AI song recommendation tool that tries to understand the vibe and feel of a song. A dataset of songs and their descriptions of moods and vibes is generated by promoting an LLM. Each song's vibe is encoded using a transformer model and saved as a vector index. Then this vector index is queried by similarity using the vector embedding of the user's input and the top N matches are returned.

Logistics Doors open at 6.30 pm (get there early as you have to sign-in via building security), talks start at 7 pm, drinks from 9 pm in the bar. We will have reduced capacity for this event but there will be plenty of people to discuss data science questions with!

Please unRSVP in good time if you realise you can't make it. We're limited by building security on the number of attendees, so please free up your place for your fellow community members!

Follow @pydatalondon (https://twitter.com/pydatalondon) for updates and early announcements.