Roman Grebennikov

Roman Grebennikov

A principal ML engineer and an ex startup CTO working on modern search and recommendations problems. A pragmatic fan of open-source software, functional programming, LLMs and performance engineering.

Sessions

How [not] to evaluate your RAG

Talk
17. June 2025, 12:00 - 12:40
Palais Atelier
How do you know if your RAG system is actually working? We’ll share a real-world case study on evaluating RAG in production—tackling messy data, chunking fails, and unexpected chatbot behavior—so you can measure quality with confidence.