Machine Learning Engineer. I build fast, scalable AI systems—LLM inference, diffusion models, and distributed infrastructure.
Stuff I've built
- Diffusion model that generates maze solutions frame-by-frame.
- Chrome extension that actually makes long ChatGPT chats usable.
- LLM inference engines serving 1k+ req/min.
- Distributed speech-to-text pipelines (20k+ recordings/day).
- Real-time clustering for millions of data points.
- More.