About me

Hi! I’m a machine learning hardware architect at Google, where I work on TPU architecture and HW/SW co-design.

My work focuses on HW/SW co-design and performance modeling for the scale-up networks of next-generation TPUs. I build analytical and cycle-level performance models to guide architecture and perf/TCO decisions. I also work on collective communication for large-scale LLM training and serving.

I received my Ph.D. in Electrical Engineering from Stanford University, advised by Prof. Mark Horowitz, where I worked on coarse-grained reconfigurable arrays (CGRAs) for image processing and machine learning. Before that, I received my B.S. in Electrical and Computer Engineering from Seoul National University.