Yushan Su is a Machine Learning Engineer at Waymo with nine years of experience building high-performance ML systems and a Ph.D. in Computer Science from Princeton. His research and engineering work focuses on model-system co-design to make foundational models and transformers significantly more efficient, including shipping sparse kernels (OPT-C/OPT-JIT) and PruMUX for throughput improvements. He has a strong track record of turning systems research into real speedups—examples include 5.9–20x training and 2.0–8.4x inference gains on sparse networks and 4.2–22x Transformer inference throughput via data multiplexing. Yushan’s background spans industry internships at AWS and Intel working on compiler kernels, GPU graph models, and FPGA-accelerated MRI reconstruction, reflecting a rare combination of compiler, hardware, and ML expertise. Based in Mountain View, he brings both deep academic rigor and production-focused pragmatism to infrastructure challenges for large-scale ML.
9 years of coding experience
1 year of employment as a software developer
School of Gifted Young Bachelor of Science - BS Applied Physics, School of Gifted Young Bachelor of Science - BS Applied Physics at University of Science and Technology of China
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Princeton University
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.