Every AI, ML & GenAI interview question, grouped by topic.
Work through each track in order — they're sequenced the way real loops escalate. The first questions in every topic are free. Sign in to track your recall as you go.
LLM & GenAI Fundamentals
135Tokens, attention, context windows, sampling, prompting vs RAG vs fine-tuning, hallucinations, evals, cost and latency: the conceptual core every Applied AI loop opens with.
RAG & Agent System Design
104Retrieval pipelines, chunking, hybrid search, reranking, tool-using agents, guardrails, multi-tenancy and eval harnesses: the modal Applied AI design round at OpenAI, Anthropic, Glean and Sierra.
Coding & DSA
144Practical builds (parsers, in-memory stores, rate limiters, streaming) plus the LeetCode-medium staples, calibrated to the practical coding screens applied AI teams actually run.
Machine Learning & Data Science
126Classical ML, embeddings, metrics (precision/recall, AUC, calibration), experiment design and statistics: the modeling fundamentals applied AI roles still test alongside GenAI.
SQL & Data Engineering
58Window functions, gaps-and-islands, Spark internals, lakehouse design, idempotent pipelines and CDC: the data plumbing under every production AI system.
System Design for AI in Production
119Productionizing a POC: latency and throughput budgets, idempotency and retries, caching, observability for non-deterministic systems, and private or air-gapped deploys.
MLOps & ML Engineering
60CI/CD for models, drift detection and retraining, model registries, Kubernetes inference, feature stores, and staging-to-production promotion: what every ML-platform loop drills.
ML Infrastructure & GPUs
70GPU/TPU memory, distributed training and parallelism, quantization, inference serving (vLLM, batching, KV cache), and scaling API gateways: the infra depth the labs and NVIDIA probe.
AI Security, Privacy & Governance
67Prompt-injection defense in depth, PII handling, tenant isolation, abuse and consumption controls, audit trails, and SOC 2 / EU AI Act questions enterprise-facing applied AI work must survive.
Behavioral & Project Deep-Dives
62Owning ambiguous ML projects end to end, the model-failure post-mortem, cross-functional trade-offs, and the deep-dive on a system you actually shipped: the highest-variance, least-prepped rounds.
ML System Design (Product)
12Design the model behind a product surface: feed ranking, recommendations, watch-time and ETA prediction, fraud and bot detection, ads ranking. Candidate generation, feature and label design, training, offline and online evaluation, and serving at scale, the way Meta, Google, Netflix and recsys teams run the round.