Location: Brazil at the moment, nomadic
  Remote: Yes
  Willing to relocate: Maybe
  Technologies: PyTorch, Deep Learning, LLM, Diffusion models, NumPy, JAX (a bit), CUDA, C/C++ | SvelteKit, TypeScript, tailwind, drizzle, Pi, Agents | DevOps (has hands/brain)
  CV: https://alexey.work/cv?ref=49522896
  Email: alexey.zaytsev@gmail.com

I fluctuate between:

- Deep learning / Neural networks - from architecture to inference. You might have used my ♥ Lovely Tensors library if you work with PyTorch (or JAX). CUDA, pytorch profiler, etc.

https://github.com/xl0/lovely-tensors https://github.com/xl0/lovely-jax https://github.com/xl0/lovely-numpy

https://github.com/xl0/tidygrad - autograd from scratch https://github.com/xl0/latent-tools https://github.com/xl0/nvml-tool - manage nvidia CPU fans/power

- Full-stack AI-adjacent applications - the usual LLM API tool-calling agentinc AI + full-stack, ideally with SvelteKit.

https://chat.alexey.work https://lovely-docs.github.io https://pelican.alexey.work/gallery

I really got into Pi recently. Some cool stuff: https://github.com/xl0/pi-lovely-ide if you like to interact with the code. Check linked projects from there.

https://www.npmjs.com/package/grok-mermaid - 1.5M weekly downloads.

In my past lives: Linux kernel, Molecular Biology Masters degree, Electronics engineering in Shenzhen.