I graduated from University of Tokyo in 2011 and moved to Silicon Valley in 2013. Currently, I am working on CUDA Math Libraries at NVIDIA. Before that, I was a member of Brain-Machine-Interface team at Neuralink. Previously, I have programmed the largest computer chip (waferscale) built to date at Cerebras Systems. And prior to that, I have spent 5 years at IBM Research Almaden in Machine Intelligence group, where I was involved in multiple projects spanning Machine Learning, Performance Optimization and Hardware design. I am often asked to classify what I do as software or hardware research, but to me computer science means both. Therefore, I work on ideas which bring artificial intelligence, hardware and software together.
twitter: @rockikamil
github: krocki
linkedin: krocki
medium: @kamil.rocki
scholar: profile
resume: 
Demystifying Computer Architecture