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.
63 results across 1 active filter
Page 2 of 3
Chooses Vertex AI shared or reserved capacity using traffic shape, reliability, geography, cost, and workload prioritization.
Combines low-friction ratings, structured reasons, behavioral outcomes, review queues, and privacy-aware eval case creation.
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.
Designs a bounded and reversible first AI feature with measurable value, controlled data, validation, evaluation, observability, fallback, and human oversight.
Defines safe fallback, reduced capability, stale or cached behavior, and feature disablement without hiding changed guarantees.
Treats streams as event protocols with partial-output UX, cancellation, validation, moderation, and terminal outcome semantics.
Separates traffic, data, dependency, model, prompt, and grader change while maintaining stable anchors and fresh evaluation.
Creates a task-oriented model boundary that normalizes application outcomes without erasing useful provider capabilities.
Allocates per-stage deadlines and spend, controls tokens and fan-out, and optimizes for successful outcomes rather than cheap calls.
Controls admission, concurrency, queues, tenant fairness, token budgets, and overload behavior before provider throttling cascades.
Combines application authorization, scoped platform resources, tenant budgets, admission control, usage attribution, and noisy-neighbor protection.
Coordinates source changes, versions, tombstones, reconciliation, and query-time freshness without treating the index as authoritative.
Uses stable operation identities, persisted states, deduplication, side-effect keys, and replay rules across requests and workers.
Separates durable application state from the model's bounded request context while preserving ownership, concurrency, and deletion.
Rebuilds and compares incompatible vector spaces using versioned indexes, shadow queries, atomic cutover, and rollback.
Uses infrastructure and configuration as code, immutable behavior versions, environment-specific resources, evaluation gates, and drift detection.
Checkpoints authoritative state, reconciles ambiguous tool outcomes, preserves approvals, and resumes without repeating completed work.
Uses constrained output where possible, deterministic parsing and validation, bounded targeted repair, and safe fallback.
Contains compromised AI capabilities, preserves evidence, scopes derived data and actions, remediates boundaries, and verifies safe recovery.
Treats model changes as controlled releases using versioned configuration, fixed evaluations, shadow or canary traffic, monitoring, and rollback.
Uses explicit capability and risk policy to route by task while preserving evaluation, version attribution, budgets, and fallback semantics.
Combines deterministic invariants, severity-aware quality thresholds, slice protection, baseline comparison, and guarded rollout.
Uses inference profiles for capacity while accounting for destination Regions, IAM and SCP policy, residency, quotas, and observable routing.