What RAG evaluation interviews test beyond recall@k
7 min read A wrong RAG answer is either a retrieval failure or a generation failure, and the interview is mostly about proving you can tell which. Read article
AI/ML Interview Questions
AI/ML Interview Questions
Hebbia interview guide: what they ask retrieval and ML engineers
7 min read A grounded look at Hebbia’s engineering interview loop, the retrieval and applied-ML questions they ask, and how to prepare for a company that thinks standard RAG is a dead end. Read article
AI/ML Interview Questions
What applied-AI engineer interviews test in 2026
6 min read The AI engineer loop stopped looking like a classic ML interview, and the RAG, agent, and evaluation rounds are where candidates get sorted. Read article
AI/ML Interview Questions
What LLM interviewers actually ask about transformers
7 min read A quick reference for the attention, tokenization, KV-cache, RAG, and evaluation questions that come up in LLM and machine learning interviews. Read article
Interview Prep
What Glean’s engineering interview actually tests
7 min read Glean’s engineering loop leans on a search-and-retrieval system design round and a two-hour practical build that trips up candidates who only prepped algorithms. Read article
AI/ML Interview Questions
What GenAI engineer interviews test that ML ones don’t
6 min read The GenAI engineer loop looks like a machine-learning loop until you hit the retrieval design and evaluation rounds, where most candidates quietly fall apart. Read article
System Design
What interviewers actually grade in a RAG design round
6 min read What separates a passing RAG design answer from a hand-wavy one, stage by stage. Read article
Tools & Reviews
When pgvector is enough and when you actually need Pinecone
6 min read A practical look at when pgvector covers your vector search and when Pinecone or Weaviate earns its extra cost and operational overhead. Read article
AI/ML Interview Questions
What is RAG? Retrieval-Augmented Generation vs Fine-tuning
5 min read Retrieval-Augmented Generation (RAG) is one of the most widely deployed LLM patterns in production. Understanding when to use RAG versus Read article
