Question bank
4,310 interview questions, answered.
Reference answers, what the interviewer is really testing, how it is graded, and the follow-ups that come next.
Easy 4Medium 31Hard 15
Filters · onDifficulty, topic, company
15 questions
- 1Design a language model that minimizes harmful outputs while remaining useful and expressive.HardSystem design· 30 min·
Anthropic - 2Evaluate LLMs on a toy task and use LLMs to generate additional evaluation data.Hard· 30 min·
Anthropic - 3How do you approach generative-AI safety in a consumer product?HardProduct· 20 min·
Google, Anthropic - 4When is a prompt cache calculated, and what is a model harness?Hard· 20 min·
Anthropic - 5Write code rapidly to a specification, then refactor it as new constraints are introduced.HardCoding· 20 min·
Anthropic - 6Debug an actual LLM inference step in a 20–30 line Colab skeleton (Anthropic)HardCodingSystem design·
Anthropic - 7Design a distributed training pipeline for an LLM with fault toleranceHardCodingSystem design·
Anthropic - 8Design a system for safe deployment of AI models in productionHardCodingSystem design·
Anthropic - 9Optimize a Python-simulated TPU kernel to beat 1487 cycles (Anthropic performance take-home)HardCodingSystem design·
Anthropic - 10Design a key-value store.HardSystem design·
Accenture, Anthropic - 11Design an inference batching system for a single GPU that can handle up to 100 inputs per batch while users wait synchronously, maximizing utilization under compute constraints.HardAI MLSystem design·
Anthropic - 12Implement LRU Cache.HardCoding·
Accenture, Adobe - 13Describe your process for developing a marketing strategy for new products, especially in highly competitive industries like consumer electronics.HardTechnical·
Anthropic - 14Describe a challenging project you worked on and what made it difficult.HardBehavioral·
Amazon, Anthropic - 15Describe the most technically complex project you have worked on and explain why it was complex.HardBehavioral·
Amazon, Anthropic