testing

Evals are the #1 probing area in AI-lab FDE loops. The full suite design, golden sets, component metrics, safety red-teaming, CI gates, and the launch-blocking thresholds, in interview-ready form.

The format that filters out LeetCode-only candidates: unfamiliar code, failing tests, 45 minutes. There's a repeatable protocol for it, and a reason the first five minutes decide the round.

The coding question that doubles as a RAG-fundamentals check. Greedy packing is easy; the oversized-sentence case, the overlap-progress trap, and the tests you write unprompted are what AI-lab interviewers actually score.

The OpenAI variant where the data structure is the warm-up: the round is graded on whether your tests control time and whether you can argue global vs per-key vs optimistic locking with actual reasons. Most candidates ace part one and lose the round in parts two and three.

When the model writes the code, your job shifts to specifying and checking it. The strong answer is a multi-layer validation pipeline that tests behaviors and contracts, not strings, plus the uncomfortable reframe that testing is now the bottleneck skill, not typing.

The instinct is to grade the codebase. Grade the feedback loop instead: a repo with no docs and a 90-second test command is friendlier to an agent than a beautifully documented one whose suite takes 40 minutes and flakes 8% of the time, and the arithmetic on that second number is worse than it looks.

'We checked accuracy' is the answer that ends interviews. The five-layer test pyramid for ML pipelines, data contracts, transform unit tests, behavioral checks, serving tests, shadow validation, with the gates that actually block promotion.

A reported AI-security interview staple with a known grading rubric: recon, bypass, leakage, tool abuse, multi-turn drift. Candidates who free-associate attack ideas fail; candidates who run a structured campaign pass.