I study Computer Science at the University of Waterloo. I did research on machine learning performance optimizations like speculative decoding and sparsity at Databricks on the Mosaic Resesarch Performance team.

Previously, I was a software engineer at Tesla Autopilot, researching efficient quantization such as FP8 on large vision models along with improving the training systems on Dojo. Before that, I worked on Large Language Models at Cohere as an early engineer, focusing on model inference and machine learning systems.

My academic interests include Machine Learning (especially in Deep Learning training dynamics, performance, and NLP), hard software problems in Distributed Systems and PL/Compilers, and Education (broadly and specifically in CS and Math).

Other things that take up my time include reading, learning about the histories and philosophies of both science and art, crosswords, exercise (nowadays lifting, running, and swimming).