RAG Engineer

Name two situations where Flat brute force search is still the correct production choice in a 2026 vector pipeline.

Pre-filter versus post-filter strategies for metadata-constrained ANN search — what breaks at each extreme?

Aggressive metadata filtering can silently destroy recall on an HNSW index even when matches exist. Why?

What problem does DiskANN solve that HNSW does not, and when do you reach for it?

Doubling the embedding dimension from 768 to 1536 — what changes in storage, query latency, and PQ trainability?

Select all dimensions that meaningfully drive cost on a managed vector database bill in 2026.

A team's Pinecone bill 5x'd month over month with no traffic change. Order the most likely causes to investigate, from most likely to least likely.

Cosine similarity and dot product give identical rankings under exactly one condition. Which is it?

When does binary quantization beat Product Quantization as the production compression choice for a vector index?

Why does every production retrieval system use approximate nearest-neighbor search instead of exact search past a certain corpus size?

Bi-encoders vs cross-encoders, where does attention cross the query and document?

A RAG pipeline just shipped for internal docs. How would the team know if retrieval is actually helping?

Building a golden dataset for RAG eval from scratch: walk through the steps and name the mistake that wastes the most labeling budget.

A colleague claims their model is 'grounded' because it cites sources. Explain why citation presence alone does not prove factual grounding.

MCP has tools, resources, and prompts. What makes a resource different from a tool?

Your indexing pipeline tokenizes 10M docs in 18 hours. What single change gives the biggest speedup?

Flashcard: how is agentic RAG different from single-shot RAG?

You have 500KB of relevant documentation that exceeds the 200K-token context window of your production model. How should you choose between context stuffing (fit what you can) and RAG retrieval?

Flashcard: what is a vector database, and why does RAG need one?

Flashcard: what is similarity search in RAG, and how does it differ from keyword search?

Flashcard: what does 'grounding' mean in the context of RAG, and why is it the whole point?

Flashcard: what is an embedding in a RAG pipeline, and what role does it play?

Flashcard: what does chunking mean in RAG, and why do we chunk at all?

Your team is comparing a vanilla LLM chatbot against a RAG chatbot. What is the single most important difference between them at query time?

Your team is tuning top-k for the retriever in a production RAG system. What is the strongest reason NOT to just push top-k to its highest possible value?