Cody Yu is an experienced systems engineer with 11 years building high-performance ML infrastructure, currently a Member of Technical Staff at OpenAI focusing on post-training infrastructure. He previously led LLM inference performance efforts as Staff Software Engineer at Anyscale and was a founding engineer at Boson AI, designing large-scale LLM serving and evaluation platforms. His background includes deep learning compiler and distributed training work at AWS and research-driven compiler and FPGA acceleration at Falcon Computing and UCLA, culminating in a PhD in computer science. Comfortable shipping production systems and research prototypes, Cody blends low-level compiler know-how with practical ML-serving expertise and a cultural devotion to Python. A detail not obvious from titles: he’s repeatedly owned end-to-end automation for tuning and scheduling in distributed ML stacks, turning research ideas into production-grade tooling.
Contributions:36 pushes, 1 branch in 2 years 4 months
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.