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 190Medium 2,498Hard 982
Filters · onDifficulty, topic, company

982 questions

  1. 145How would you build an evaluation suite for text-to-speech?Hard· 20 min
  2. 146How would you build an evaluation suite for vector databases?Hard· 20 min
  3. 147How would you build an evaluation suite for video generation?Hard· 20 min
  4. 148How would you build an evaluation suite for vision-language models?Hard· 20 min
  5. 149How would you build an evaluation suite for voice cloning?Hard· 20 min
  6. 150How would you capacity-plan an inference service with bursty traffic?HardSystem design· 30 min
  7. 151How would you debug an AI deployment using a customer’s private data?HardTechnicalCoding· 30 min
  8. 152How would you decide between prompting, RAG, fine-tuning, and training a model?Hard· 20 min
  9. 153How would you defend an LLM application against prompt injection?HardTechnicalSystem design· 30 min
  10. 154How would you define success metrics for a generative-AI product?HardProductData· 20 min
  11. 155How would you design an AI assistant for doctors?HardProduct· 30 min
  12. 156How would you design multi-tenant retrieval without leaking customer data?HardTechnicalSystem design· 30 min
  13. 157How would you detect memorization or sensitive-data leakage from a model?Hard· 30 min
  14. 158How would you detect model drift in a generative-AI application?HardSystem design· 20 min
  15. 159How would you evaluate a multi-agent system?HardSystem design· 30 min
  16. 160How would you evaluate a RAG pipeline end to end?HardAI ML· 20 min
  17. 161How would you evaluate whether an enterprise AI pilot is ready for production?HardProduct· 20 min
  18. 162How would you handle citations and provenance in an AI research product?HardProduct· 20 min
  19. 163How would you implement semantic caching safely?HardSystem design· 20 min
  20. 164How would you improve the quality, latency, and cost of a AI developer platforms system without masking regressions?HardSystem design· 30 min
  21. 165How would you improve the quality, latency, and cost of a AI incident response system without masking regressions?HardSystem design· 30 min
  22. 166How would you improve the quality, latency, and cost of a AI watermarking system without masking regressions?HardSystem design· 30 min
  23. 167How would you improve the quality, latency, and cost of a content moderation system without masking regressions?HardSystem design· 30 min
  24. 168How would you improve the quality, latency, and cost of a continual learning system without masking regressions?HardSystem design· 30 min