I'm a System Software Engineer working at NVIDIA. I mainly work on Triton Inference Server and Model Analyzer.

Previously, I was an MASc student in the Electrical and Computer Engineering department at the University of Toronto. My interests lie at the intersction of Machine Learning and Computer Systems. My previous research projects include Co-Location of Deep Learning Training Jobs in GPU Clusters and Adaptive Gradient Quantization for Data-Parallel SGD.

Profile Picutre