Skip to content

Topic guide

LLM interview questions, organised by what they test

Direct answer

LLM interview questions are best prepared by theme rather than by volume. Nine themes cover almost all of them: model fundamentals, inference and serving, retrieval, agents and tool use, evaluation, reliability and safety, cost and latency, production debugging, and project judgment. Interviewers rarely score the first answer — they score the follow-ups, which is why memorised responses collapse and reasoning from a real system holds up.

This is a map of what gets asked and why, not a question bank. Each theme links onward to the deeper guide where one exists.

Updated September 15, 2026 · Patterns, not promises. This page describes how these loops usually run. It makes no claim about any specific company’s interview.

Why question banks stop working after the first follow-up

A memorised answer is a single move in a conversation that lasts five. An interviewer asks how you would evaluate a summarisation feature, you produce a fluent paragraph about eval sets, and then they ask what your eval set contained, how you labelled it, how many examples, who disagreed, and what the metric did when you changed the prompt. The script runs out immediately.

This is not a trick. It is how experienced interviewers distinguish someone who has read about a practice from someone who has run it. The reliable defence is to anchor every theme below to one system you actually worked on, so the follow-ups have somewhere real to go.

It also means volume is the wrong target. Being able to recognise three hundred questions is worth less than being able to go four levels deep on nine themes.

The nine themes

For each theme: what interviewers are probing, and the follow-up that usually separates candidates.

1. Model fundamentals
Probing: whether you understand what a model can and cannot be relied on to do — context limits, tokenisation effects, determinism, and why a temperature change is not a quality strategy. The separating follow-up is usually "why does that happen?" rather than "what is it called?".
2. Inference and serving
Probing: token accounting, prompt and prefix caching, batching, streaming, context window management, and hosted versus self-hosted trade-offs. The separating follow-up is what actually dominates your p95 today.
3. Retrieval and RAG
Probing: ingestion, chunking, embeddings, hybrid search, reranking, and context construction. The separating follow-up is what you do when the top results are irrelevant, and how you detect that in production.
4. Agents and tool use
Probing: state, tool interface design, orchestration, termination, idempotency and recovery. The separating follow-up is how the agent stops when it is going wrong.
5. Evaluation
Probing: golden sets, task metrics, judge models used carefully, human review, offline against online. The separating follow-up is a regression your evaluation actually caught, and what it cost to build.
6. Reliability and safety
Probing: grounding, refusal behaviour, guardrails, prompt injection through retrieved or tool-supplied content, and the false-positive cost of every filter you add.
7. Cost and latency
Probing: where money and time are spent, and which lever you pull first. The separating follow-up is whether you measured before optimising.
8. Production debugging
Probing: instrumentation, tracing a single bad output back to its cause, and distinguishing a retrieval failure from a prompt failure from a model change.
9. Project judgment
Probing: what you chose not to build, when you decided a model was the wrong tool, and what you would do differently. This theme appears in every round, not only the behavioral one.

What to ask your recruiter

Before you prepare anything, send one short email: how many rounds, what each one is called, how long each runs, whether any of them is a take-home, and whether an AI assistant is allowed in the coding round. Recruiters answer this routinely. Anything they confirm outranks every pattern on this page, because it is first-party evidence about your loop rather than a general tendency across companies.

Which themes appear in which round

A rough allocation. Use it to decide where to spend preparation once your recruiter has confirmed the round names.

RoundDominant themesUsually absent
LLM / AI system designServing, retrieval, evaluation, reliability, cost.Model internals, trivia about recent releases.
Evaluation roundEvaluation, reliability, production debugging.Architecture internals.
Practical codingProduction debugging, tool use, sometimes retrieval.Cost modelling, safety policy.
Project deep diveProject judgment, debugging, evaluation, cost.Nothing, in practice — deep dives roam.
BehavioralProject judgment.Everything technical, though examples should still be concrete.

A structure that survives follow-ups

Use it for any theme. It signals experience because it is the order in which the work actually happens.

  1. 01State the decision you are being asked to make, in one sentence, so you and the interviewer are solving the same problem.
  2. 02Name the constraint that decides it: latency, cost, privacy, data availability, or risk.
  3. 03Give your answer and the trade-off you accepted, explicitly. An answer with no cost attached reads as untested.
  4. 04Say how you would know you were wrong — the metric, the trace, or the eval case.
  5. 05Ground it in one real instance from your own work, including a number if you have one and a clear "I do not remember" if you do not.

Study now, review, skip

Study now

  • Themes 3, 5 and 8: retrieval, evaluation, production debugging. These carry the most weight in most loops.
  • One real system you can use as the anchor for every theme.
  • Theme 7 with real numbers from that system.

Review

  • Themes 2 and 4: serving and agents, unless the role centres on them, in which case they move up.
  • Theme 6, especially injection through retrieved content.

Skip

  • Memorising architecture internals beyond what you need to reason about behaviour.
  • Long question lists. Depth on nine themes beats recognition of three hundred prompts.
  • Anything claiming to be a specific company's exact questions.

Common failure modes

  • Fluent first answers with nothing behind them, which the second follow-up exposes.
  • Naming tools and frameworks instead of describing decisions and trade-offs.
  • Using a public benchmark as a stand-in for a task-specific evaluation.
  • Claiming numbers from memory that do not survive arithmetic.
  • Answering a judgment question with a technique, when the interviewer asked what you would decide.
  • Never saying "I do not know", which reads as less trustworthy rather than more competent.

FAQ

Common questions

Is there a list of the most common LLM interview questions?
Lists exist, but they age badly and none of them is specific to your loop. The themes above are stable; the phrasings change constantly. Preparing the reasoning behind a theme transfers to any phrasing of it.
Do interviewers ask about transformer architecture?
In product engineering loops it is uncommon, and usually only at the level of what the architecture implies for behaviour. Research and inference-infrastructure roles are different, and the job description normally makes that obvious.
How technical do the answers need to be?
Specific rather than technical. A concrete account of one system, with the constraint that decided each choice, consistently outperforms a general explanation of best practice.
What if I am asked something I have never done?
Say that, then reason out loud from the nearest thing you have done. Interviewers score the reasoning. Improvised experience is detected quickly and costs far more than the admission would have.

How every ranking on this site is reasoned about, including what counts as evidence: read the methodology.

Stop guessing which of these you get

Map your actual interview.

This page is the general pattern. Paste the job you are actually interviewing for and the wording your recruiter used, and the map ranks the rounds you are likely to face, explains why each is ranked where it is, and tells you what to skip.

Build my free Interview Map

Free. No card. See your map before deciding whether to unlock the full one.

See a complete Full Interview Map example