RAG Interview Questions #17 - The Lexical Replacement Trap

Why upgrading your search stack to vectors isn't a fix, but a trade-off that silently drops high-intent queries, and the score fusion trick elite engineers use to survive it.

You’re in a Staff ML Engineer interview at OpenAI and the interviewer asks:

“Your team wants to swap lexical query expansion for semantic expansion to boost precision. Walk me through why that’s the wrong way to do the migration.”

Don’t say: “Lexical expansion adds synonyms for recall, semantic expansion uses embeddings for intent, so we upgrade to the be…