The 60-second answer
Define the knowledge boundary, chunking strategy, metadata, embeddings, and retrieval/index design. Separate retrieval quality from generation quality: measure recall/precision or nDCG, then faithfulness, citation correctness, task quality, safety, latency, and cost.
Build the answer in this order
Define the knowledge boundary, chunking strategy, metadata, embeddings, and retrieval/index design.
Separate retrieval quality from generation quality: measure recall/precision or nDCG, then faithfulness, citation correctness, task quality, safety, latency, and cost.
Add reranking, evidence-aware prompting, insufficient-evidence fallbacks, and trace retrieval/model behavior for debugging.
Test prompt injection, stale data, permissions, and corpus/model/version changes before production rollout.
A useful interview mental model
This is the shape of a strong answer—not a script to memorize.
Senior-level signal
- Version corpus, embeddings, reranker, prompt, and model independently so regressions are attributable and reversible.
- For enterprise RAG, enforce authorization before retrieval and evaluate leakage/exfiltration attacks as first-class failure modes.
What the interviewer is really testing
Likely follow-up questions
Common weak-answer patterns
- Jumping to a model before defining the product contract.
- Listing components without bottlenecks, metrics, or failure handling.
- Ignoring data quality, serving latency, monitoring, and iteration.