RAG Interview Questions, issue 5, Jul 9, 2026

The Leaderboard Trap

Search Infrastructure Engineer interview at Google, and the interviewer asks:

We benchmarked dense retrieval against BM25 on our eval set. Dense won on every metric. Do we rip out sparse retrieval entirely?

Don’t say: Yes, dense captures semantic meaning, sparse is just keyword matching. Dense is the higher-resolution version of the same idea.

Why dense retrievers look invincible on evaluation sets but fail catastrophically in production, and the rank fusion architecture that actually gets you hired.

The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.

Read it on Substack

Get the next one

Free on Substack. Unsubscribe in one click.