OpenAI still asks you to design TinyURL. Mistral asks about mixture of experts.

• 60% of OpenAI’s design questions are classic system design, like TinyURL, YouTube and a payment system. At Mistral AI, 0 of 12 are.
• 60% of all design questions are about AI systems and ML. At Anthropic it is 71%.
• “Design a RAG system over company docs” comes up at 5 companies, more than any other design question; “Evaluate a new LLM before launch” at 4.
• LLM serving and GPUs is the largest AI theme: 13 of 60 AI design questions.
• 29% of design questions are asked in the technical screen, not only in design rounds.

OpenAI leans classic; Anthropic and Mistral AI lean AI

Each company’s design questions by type. Classic system design is the product kind (TinyURL, a chat app, a payment system); AI system design is serving, RAG and agents; ML design is models, training and evals. Cohere, Perplexity, Scale AI, Cursor (SpaceXAI) and Google DeepMind have fewer than 10 design questions and are left out.

5 companies ask the same RAG question

Design questions reported at more than one company. “Design a RAG system over company docs” comes up at Anthropic, Cohere, Perplexity, SpaceXAI (xAI) and OpenAI.

1. Design a RAG system over company docs5 companies
2. Evaluate a new LLM before launch4 companies
3. Design ChatGPT3 companies
4. Design an LLM inference serving platform3 companies
5. Design Google Docs2 companies
6. Design TinyURL2 companies
7. Design a CI/CD system2 companies
8. Design a GPU scheduling platform2 companies

LLM serving and GPUs lead the AI questions

The 60 AI system and ML design questions, each counted once, by what they are about.

1. LLM serving and GPUs13
2. Evals and safety10
3. Training and post-training9
4. RAG and search8
5. Agents6
6. Research and experiments4
7. Other ML and data4
8. LLM apps and tools3
9. Model internals3

29% of design questions are asked in the technical screen

Design questions by the round they were asked in, where candidates said. The technical screen asks them too.

1. Technical screen29%
2. System design28%
3. ML design16%
4. AI system design15%
5. Design review5%
6. Take-home2%

What this means for your prep

1. At OpenAI, prep classic system design as well as AI. 60% of its design questions are the classic kind.
2. Everywhere else, lead with AI systems. The largest themes: LLM serving and GPUs (13), evals and safety (10), training and post-training (9).
3. Practice the shared questions first: Design a RAG system over company docs, Evaluate a new LLM before launch, Design ChatGPT and Design an LLM inference serving platform.
4. At Mistral AI, know the model itself. Its questions cover mixture of experts, parallelism, normalization and optimizers.
5. Have a short design answer ready for the screen. 29% of design questions come up there.