AI engineer interview questions
AI engineer interviews at the top AI labs ask AI system design (LLM serving, retrieval, agents, evals) and ML design, on top of coding. Here are 78 AI system design questions and 150 ML design questions asked at Anthropic, Meta, Microsoft, OpenAI, Amazon and Databricks and more, most asked first, each dated by when it was last asked.
AI system design 78
All 78 →- Batched LLM inference API over GPUs · Anthropic, BasetenOct 2026
- Design a video generation service on a scarce GPU pool · OpenAI, GoogleSep 2026
- Design an AI prompt playground · Anthropic, OpenAIOct 2026
- Design a distributed AI model downloader · AnthropicOct 2026
- Design a RAG question-answering agent over a firm's documents · HarveySep 2026
- Design an enterprise research agent with internal and web sources and citations · CohereOct 2026
- Design a GPU scheduling platform · OpenAI, Anthropic, DatabricksSep 2026
- Design an LLM chatbot with RL-trained answers · MetaSep 2026
- Rule-driven file review agent · HarveySep 2026
- Design an AI chatbot app · OpenAI, Microsoft AI, MicrosoftSep 2026
- Retrieve tables and notebooks for a data-aware coding agent · DatabricksSep 2026
- Design durable execution for long-running agent queries · PerplexitySep 2026
- Design an AI gateway · DecagonFeb 2026
- Design a RAG assistant with agentic tools · MicrosoftFeb 2026
- AI-agent security detection over streaming telemetry · AmazonOct 2026
ML design 150
All 150 →- ML fundamentals deep dive for ML roles · Google, Amazon, MetaOct 2026
- Transformer and attention fundamentals · Amazon, Netflix, NvidiaSep 2026
- Design a harmful content detection system · Databricks, MetaSep 2026
- GPU and inference performance fundamentals · NvidiaAug 2026
- Design a large-scale recommendation system end to end · MetaJul 2026
- Deep learning frameworks and compilers: from NumPy to PyTorch and JAX · NvidiaSep 2025
- Train a model to extract highlight snippets from text · FigmaOct 2026
- Design a work-together distance between two employees · GleanSep 2026
- Implement multi-head self-attention · Apple, Meta, UberSep 2026
- ML design for retrieval: embeddings, hybrid search and ranking · OpenAI, MicrosoftSep 2026
- Matmul performance modeling on a fixed GPU · AnthropicSep 2026
- Design a personalized search ranking system · Airbnb, Uber, AmazonSep 2026
- Design a pipeline around embedding and classification services · Scale AIJul 2026
- Design a recommender for local sports teams and news · MicrosoftJun 2026
- Design candidate search for a talent marketplace · MercorMay 2026