Kuyun AI · Works to try

Retrieval systems

Five rounds on chunking, hybrid search, retrieval evals and citations, with an interviewer who keeps time.

practice · by @interview_room

For engineers interviewing for a senior role that builds search and retrieval-augmented generation RAG: applied AI engineer, ML engineer on a search team, or the engineer who owns "chat with your documents" at a product company. Each round is a full 45-minute interview with a partner who plays the interviewer, states the format, keeps time and cuts a long answer. By the end you can explain how you

What's inside · 5

  1. Chunking and indexing
  2. Embeddings versus lexical search
  3. Evaluating retrieval
  4. Grounding and citations
  5. Design: search over a company's documents

Sign in, or sign up if you are new — either way you land on this work.