Skip to content
Back to the full dashboard →

Resume generator

Andrej: resume templates

Five free resume templates built from @karpathy’s GitHub profile - switch between Markdown and LaTeX, edit anything, then copy or download. No signup.

Contact details, experience and education saved in the resume builder on the profile page are filled in here automatically on this browser.

The classic single-column order recruiters and ATS parsers expect - the same layout as the PDF export.

Source - editable

Edit freely - your changes update the preview and the copy/download output instantly.

Mode compatible preview

Andrej

github.com/karpathy | twitter.com/karpathy | Stanford

Summary

I like to train Deep Neural Nets on large datasets. Software developer working primarily in HTML, Jupyter Notebook, Python, with 54 public repositories on GitHub, including 490,718 stars earned and 878 contributions in the past year.

Projects

autoresearch - Python, Jupyter Notebook (2026)

AI agents running research on single-GPU nanochat training automatically

nanoGPT - Python (2022 – 2025)

The simplest, fastest repository for training/finetuning medium-sized GPTs.

nanochat - Python, Jupyter Notebook, Shell (2025 – 2026)

The best ChatGPT that $100 can buy.

llm.c - Cuda, Python, C, C++ (2024 – 2025)

LLM training in simple, raw C/CUDA

llm-council - Python, JavaScript, CSS, Shell (2025)

LLM Council works together to answer your hardest questions

minGPT - Python, Jupyter Notebook (2020 – 2024)

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

nn-zero-to-hero - Jupyter Notebook (2022 – 2024)

Neural Networks: Zero to Hero

llama2.c - C, Python, Jupyter Notebook, Makefile (2023 – 2024)

Inference Llama 2 in one file of pure C

micrograd - Jupyter Notebook, Python (2020 – 2026)

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

char-rnn - Lua (2015 – 2023)

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Technical Skills

  • Languages: HTML, Jupyter Notebook, Python, Cuda, JavaScript, C
  • Frameworks: Flask

Open Source & GitHub Activity

  • 54 public repositories · 490,718 stars earned · 72,108 forks across projects · 878 contributions in the past year · 15-day longest contribution streak

The preview shows the content via the Markdown twin - compile the .tex (e.g. on Overleaf) for the exact typeset output.

The one-page PDF and Word exports still live on the profile dashboard, with the editable contact and experience fields.