Hi! I'm a Data & Applied Scientist at Microsoft Azure, working on Large Language Models. In my spare time, I love taking photos, skiing, 3D printing, and reading. Sometimes I write blog posts and post photos I've taken.
Before Microsoft, I worked at Mercedes Benz Research and Development in Seattle, where I built Kubernetes enabled full stack applications and worked on distributed machine learning cloud prototypes. In the far past, I worked at Silicon Mechanics developing software to automate laying down test images over bare metal servers and clusters.
From 2016 to the end of 2018 I was a Master's student at UBC under the supervision of Mieszko Lis and Guy Lemieux, where I researched ways to prune neural networks while training, creating DropBack, achieving state of the art results in pruning WRN-28-10 on CIFAR-10 during training. DropBack enables accelerators like Procrustes that can save energy and improve performance by training with sparsity.
My current research can be found on my Google Scholar Profile
This site is not updated much anymore, as I switched to using ghost for my blogging, the link is above and here