Harvey Forward Deployed Engineer interview questions

Everyone says '500 tokens with overlap.' The candidates who get hired explain why chunk boundaries are a recall problem, name three strategies, and describe the experiment that picks between them.

A reported FDE design question that punishes one-size-fits-all answers. Each corpus has a different 'semantic unit': get the three designs, the parsing tools to name, and the eval that proves the split was worth it.

Calibrated abstention is a system property, not a prompt line. Learn the four abstention signals, the precision-at-coverage framing, and why 'just tell it to say I don't know' fails the interview.

Citations are the trust interface of enterprise RAG, and the easiest thing to fake badly. Covers inline citation generation, span verification, and the verification-rate metric that interviewers actually want.

Harvey's signature design question. The twist: the architecture is the easy half. The graded half is designing for reviewer trust, where one hallucinated clause costs more than a hundred correct ones earn.

Before you touch a model, check whether the two numbers measure the same thing. Field accuracy of 96% across twelve fields is 61% of documents fully correct, which means half of the drop may be arithmetic. The other half is the documents the pilot never saw.

Recall@10 is 0.94 and climbing, and answer accuracy is going down. The two facts are consistent, and reconciling them is the whole question: every passage you add to raise recall also adds a distractor the generator has to survive.

A classic FDE take-home shape: messy real documents in, structured index out. The grade is in the seams between reader, extractor, and writer, and in what happens when one file is garbage.

This is the shape of the TypeScript debugging round at the agent companies: a forty-line stream handler that mostly works. Each bug has a one-line demonstration, and none of them is in the model. One is a stale closure, one is a decoder splitting a multibyte character, and one is a render per token.

The signature coding problem at a legal-AI company, and it is interval merging wearing a product costume. The candidates who struggle are the ones who start matching before deciding what a match even is.

Five LLM agents over a hundred steps, and the bar is zero contradictions with a 500-page contract. The real test is the state and grounding layer, not the agent prompts.

The abstain path is designed last and decides whether the deployment is adopted. Routing to the right person, an SLA the queue can actually meet, and what happens to the case the agent already half-processed before it gave up.

FDEs change domains every deployment, so interviewers test for a repeatable learning system, and most candidates fail the second half: proving the understanding was real. Here's the method and the validation move.

Graded on two things most engineers never practice: the quality of the analogy and knowing when to stop. Here's a two-minute script that lands with a legal exec, and the depth trap to avoid.

Say 'yes' and you've failed the integrity test; say 'no' flatly and you've failed the deal. The pass is a three-beat answer that turns the question into the reason to buy. Here's the script.

The CFO ran the same prompt twice and got two answers, and now thinks the system is broken. The analogy that lands in one sentence, the honest framing that keeps trust, and the exact case where you'd set temperature to zero to make it repeat.

The gap is real, the date is close, and the business is about to ask if you'll make it. The wrong first move is to start tuning prompts. The strong move is to split the failure into causes you can act on, give the business an honest forecast with options, and protect the launch even if you can't fully close the gap.

The warm-up that quietly filters out candidates who only know LLMs as a magic API. Nail the two-phase inference picture and you set up every later answer about latency, cost, and hallucinations.

Everyone can define it; few candidates know why 'advertised context' and 'usable context' aren't the same thing. The cost, latency, and attention caveats that make this answer stand out.

The warm-up that filters out tutorial-level candidates. Interviewers aren't grading the diagram, they're grading whether you know the three places real pipelines fail and how you'd see it happening.

Modern LLMs share one architectural skeleton. Learn the five components and you can read almost any model card cold, plus the single distinction that proves to an interviewer you actually understand it rather than the buzzwords.

Tokens drive your customer's bill, their latency, and the weird failures like botched arithmetic. The rough numbers every FDE should rattle off, plus the trap answers interviewers listen for.

Every FDE will face an angry customer asking this. The mechanistic explanation interviewers want (why hallucination is the default behavior, not a bug) plus the framing that defuses customer escalations.

A deceptively simple sampling question with one trap (does temperature 0 fix hallucinations?) and one senior move interviewers reward. Know which workflows want zero.

The single most common FDE behavioral question, and the 'week one' follow-up is where most candidates collapse. Here's the structure that signals you can be dropped into chaos and produce order.