AI Monitoring Interview Questions

Silent quality decay from model updates, data shift, registry bypass, and stale few-shot banks without version discipline.

Self-hosting Llama 3 is a infrastructure-heavy question for ML platform and AI engineer roles at Meta-adjacent companies. Expect deep dives on quantization, vLLM, GPU sizing, and the TCO math that determines build vs buy decisions.

500M vectors at sub-100ms p99 is a staff-level vector search design question from Uber, Airbnb, and large-scale ML platform teams. Learn sharding strategies, index tuning, and the operational trade-offs that separate senior from principal engineers.

Cursor rules are context engineering in disguise.

**Infrastructure** Managed endpoints vs batch prediction; GPU quotas.

**Model selection** Benchmark retrieval on your corpus — smaller models cheaper if recall OK.

**Common failures** Model calls nonexistent tool; args wrong type; parallel tool_calls partial failure; streaming partial JSON; user content tricks model into exfil tool args.

Latency, recall proxies, ingest lag, index size, filter rates, error budgets, and RAG downstream signals.

Cross-language prompt design covering translation drift, code-switching, locale formatting, and eval gaps in multilingual products.

Hard AI Agents interview question on anthropic computer use interview question — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on end-to-end rag observability — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on embedding model selection and migration — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on multilingual rag challenges — architecture, trade-offs, eval, and production patterns.

Scenario question on offline golden eval vs online A/B, feedback, and guardrail metrics in production.