Practiced one out loud? Paste your answer into the free self-check and get a score in 30 seconds
What the interviewer is testing
Whether you choose techniques by the problem (knowledge vs behavior), start with the cheapest loop, and know that the options combine rather than compete.
Answer framework
- Start with prompting plus a small eval set; it is the fastest loop.
- Add RAG when answers depend on private or changing knowledge, or need citations.
- Fine-tune when you need consistent format or style, a narrow task at lower cost or latency with a smaller model, domain language the base model handles poorly, or behavior long prompts cannot hold.
- Rule out fine-tuning for facts that change; retrieval handles those.
- Say they combine: a fine-tuned model plus RAG is common.
Sample answer
I start with prompting plus a small eval set because it is the fastest loop. In-context learning changes no weights and iteration is instant, but every request pays for the extra tokens and behavior is bounded by the window.
I add RAG when answers depend on private or changing knowledge. I fine-tune when I need consistent format or behavior that prompting cannot hold, lower latency or cost via a smaller model, or I have thousands of good examples. Fine-tuning needs data, evaluation and redeployment, and it is a poor way to add frequently changing facts.
They are not exclusive: a fine-tuned model plus RAG is common. Knowledge goes in retrieval; behavior goes in the weights.
Likely follow-ups
Common mistakes
- Treating RAG and fine-tuning as either/or.
- Proposing fine-tuning to teach the model facts that change often.
- Skipping the prompting baseline and the eval set that tells you whether anything improved.
- Ignoring the operational cost of fine-tuning: data, evaluation and redeployment.
- Forgetting that a smaller fine-tuned model can be a cost and latency play.
The 0 to 1 AI Engineer Interview Playbook covers the answer frameworks, system-design walkthroughs and an 8-week plan.
Get the playbook 40% off with code EARLYBF until Nov 3, 11:59 PM PTEARLYBF: 40% off until Nov 3Smaller start: Score your answers against 50 rubrics, $9. 50 AI engineer questions, one rubric each, PDF on Gumroad.
Interviewing for PM or TPM? See the full PM package, $59 on Gumroad: a resume system, a PM, TPM and PGM interview handbook, a 1:1 cheat sheet and a PM playbook. PM and TPM content, not AI engineer prep.