TorchLeet

68 PyTorch problems from real ML/AI interviews at Google, Meta, Anthropic, and more.

Follow me on Twitter | Try the Terminal | AI Tutor | Send Feedback

I struggled to grind for ML/AI interviews so I went back to the basics and created a list after careful research. These are real problems from first person reports from real engineer interviews.

[!IMPORTANT] Don't use GPT. The whole point is to struggle through these yourself. If you paste these into ChatGPT you're wasting your time. The goal is to deeply understand PyTorch, not to get an answer. I used GPT to help write some of the initial code, but I tested and solved every problem myself. That's where the learning happens.

AI Tutor (NEW)

Turn any AI assistant into your PyTorch interview coach. The TorchLeet MCP server gives your AI access to all 68 problems, progressive hints, company prep plans, and learning paths, while enforcing a no-spoilers teaching style.

# Clone the repo first
git clone https://github.com/Exorust/TorchLeet.git
cd TorchLeet

# Then connect the AI Tutor (pick your client)

# Claude Code
claude mcp add torchleet -- npx -y torchleet-mcp

# Codex
codex mcp add torchleet -- npx -y torchleet-mcp

{
  "mcpServers": {
    "torchleet": {
      "command": "npx",
      "args": ["-y", "torchleet-mcp"]
    }
  }
}

Four learning guides:

Set up the AI Tutor | torchleet-mcp on npm

68 problems across three tracks:

Questions overlap between tracks. Company-tagged questions tell you exactly what Google, Anthropic, Meta, and others ask.

Quick Start

# Install PyTorch
# https://pytorch.org/get-started/locally/

# Pick a problem, fill in the TODOs, compare with the solution
jupyter notebook torch/basic/lin-regression/lin-regression.ipynb

Each problem has a question file and a _SOLN solution file. Fill in the ... and #TODO blocks, then check your work.

LLM Learning Path

Build an LLM from scratch, one question at a time. Recommended order:

1. Foundations

2. Core Transformer

3. Full Model

4. Alignment & Fine-Tuning

5. Decoding & Inference

6. Systems

Basics

Core PyTorch and classical ML fundamentals.

Advanced

Company-tagged questions from real ML/AI interviews. Sorted by topic.

Modern Architectures

Alignment & Training

LLM Inference & Systems

GPU Systems & Kernels

Hard Foundations

Company Quick-Reference

"If I'm interviewing at X, which questions should I prioritize?" Numbers reference the v3-tagged questions above.

Contributing

Found a bug? Have a question from your own interview? PRs are welcome. Follow the notebook structure (question file + _SOLN file) and tag the authors.

If you found this helpful, follow me on Twitter. I post about ML interviews, PyTorch tips, and what I'm building next. Or just send me feedback, I read everything.

Contributors

Thanks to everyone who has added problems, fixes and solutions (11 so far):

Exorust	samhubs	AtulAravindDas	CaslowChien	emmanuel-ferdman	PadLex
bargav25	ezhoureal	Hylthek	gulbaki	jg-eno

Authors

Chandrahas Aroori Twitter | LinkedIn | Email

Caslow Chien Website | LinkedIn | Email

Stargazers