Pick a focused question that fits your time, stack, and interview goal.
How much time do you have?
Show one-drill sessions you can finish now.
1345 results
Page 27 of 57
Treats Python web workers as measured processes with separate memory, lifecycle, and failure boundaries.
Chooses Vertex AI shared or reserved capacity using traffic shape, reliability, geography, cost, and workload prioritization.
Tunes evidence quantity and no-answer behavior from measured relevance rather than treating similarity scores as universal confidence.
Combines low-friction ratings, structured reasons, behavioral outcomes, review queues, and privacy-aware eval case creation.
Selects relevant, trustworthy, and budgeted context instead of treating the context window as storage.
Bounds expensive inputs, outputs, retrieval, tools, retries, concurrency, and fan-out while preserving fair service.
Covers allocation rate, collection frequency, latency symptoms, and safe production steps for GC-heavy services.
Uses file upload processing to practice bounded memory, stream ownership, temporary files, and retained buffers.
Uses provenance, content isolation, constrained authority, behavioral checks, and deterministic enforcement to contain hostile external instructions.
Turns a product outcome into observable quality, safety, and operational criteria before selecting convenient scores.
Builds an immutable Java type through valid construction, final state, defensive copying, controlled exposure, and safe sharing.
Covers chunking, bounded concurrency, scoped dependencies, progress, retries, and avoiding full-dataset memory spikes.
Builds a focused scoring guide, representative labeled examples, bias checks, and ongoing agreement monitoring for model-based evaluation.
Builds a repeatable path from governed source documents to parsed, chunked, embedded, traceable, and replaceable index records.
Combines bounded instructions, source context, a narrow schema, abstention, semantic validation, review, observability, and rollout.
Designs a bounded and reversible first AI feature with measurable value, controlled data, validation, evaluation, observability, fallback, and human oversight.
Defines a narrow capability with a clear name, decision-oriented description, typed inputs, and safe result semantics.
Designs a narrow, typed, provider-supported schema that communicates the real downstream contract.
Combines product policy, input and output controls, context-aware handling, human escalation, appeals, and measurable safety quality.
Places validation at the right form level and manages asynchronous checks without races or noisy requests.
Defines safe fallback, reduced capability, stale or cached behavior, and feature disablement without hiding changed guarantees.
Explains health endpoints, readiness versus liveness, warm-up, dependency checks, and safe App Service health behavior.
Pauses durable execution with a clear action preview, verifies approver authority, handles expiry and changed state, and resumes idempotently.
Balances route ownership, initial bundle cost, likely navigation, authorization, and measurable user experience.