About

I’m currently at Apple working as a Research Engineer on Machine Learning. Previously I was at Nvidia & OctoML, contributing to TensorRT-LLM, PyTorch & Apache TVM on training/inference infrastructure, multi-modality and performance.

What I Write About

Machine Learning infrastructure

large-scale training infrastructure, accelerated inference, and PyTorch

Foundational ML & Algorithms

large language model, intelligence, and multi-modality

Performance and Optimization

CUDA performance, kernel engineering and compilers

Get in Touch

I'm always interested in connecting with fellow developers, designers, and tech enthusiasts. Feel free to reach out if you'd like to collaborate, discuss ideas, or just say hello!