Technical Screen

Explain why a context window is not a word count, why a model does not remember earlier chats on its own, and why temperature zero does not make an answer true.

Rewrite a vague request into a testable extraction prompt with category rules, a missing-data policy, consistent examples, and a JSON output contract, then explain why parseable JSON can still be wrong.

Explain how embeddings and exact-term matching find candidates for a query, and why the top result is a ranking signal rather than a verified answer.

Explain how documents become evidence for a generated answer, and why an answer can be wrong even when it cites a real document.

Turn a follow-up message into a standalone retrieval query, keep access filters tied to the signed-in session on every turn, and decide which turns should not retrieve at all.

Follow one ticket lookup from tool declaration to answer: what the model proposes, what the application validates and executes, and what the assistant says when the result is unavailable.

Use a request trace to tell retrieval, context-packing, and generation failures apart, and report answer quality with a named denominator next to operational signals.

Explain why a retrieved document cannot grant itself authority, and name the controls in trusted code that still hold when the model follows an injected instruction.

Explain why a slow model provider raises concurrency and retry load, using latency, throughput, rate limits, deadlines, and a bounded response strategy.

Explain what training, validation, and test splits are each for, then repair a fictional marketplace's evaluation plan by choosing a split that matches how its model will be used.

Explain how a streaming feedback UI shows partial output, what Stop really cancels, and how run IDs keep late events from an old attempt out of a new answer.

Decide whether a feedback assistant's failures call for prompting, retrieval, or fine-tuning, and explain the reviewed data, grouped split, and baseline comparison that fine-tuning would need.

Route a blurry code screenshot and a mixed PDF to suitable extraction methods, and explain the result with evidence the user can check and honest uncertainty.

Split a slow first token into queue wait, prefill, and emit from a server trace, and choose a serving configuration per workload instead of by throughput alone.

Examine a fictional AI coach whose feedback passes a human Approve button, calculate what careful review would cost, and propose the purpose, data, review, and ownership controls that make the oversight meaningful.

Explain why longer sessions do not justify shipping AI hints, then use a fictional pilot's per-arm figures to propose an evaluation with a real baseline, an independent learning outcome, and guardrails.

Explain how a coding assistant assembles its context, which component decides whether each proposed action runs, and why an instruction found inside a file cannot grant itself permission.