Phitchaya Phothilimthana

Member Of Technical Staff at OpenAI

Mountain View, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Phitchaya Phothilimthana is a hardware-software co-design engineer with 13 years of experience building efficient compilers and systems for emerging architectures, now a Member of Technical Staff at OpenAI after six years as a Research Scientist at Google. He brings deep compiler expertise from a Berkeley Ph.D. focused on generating efficient code for radical architectures and has contributed to high-impact open-source work on XLA—fixing nondeterminism, improving memory tracking, and optimizing instruction fusion for ML accelerators. His career blends rigorous research internships (NVIDIA, Microsoft, Qualcomm) with production-facing improvements, evidencing a knack for turning advanced analysis into pragmatic tooling. Based in Mountain View, he pairs low-level systems thinking with a practical orientation toward robustness and deterministic behavior that benefits large-scale ML compilation pipelines.
code13 years of coding experience
job6 years of employment as a software developer
bookUniversity of California, Berkeley
bookBachelor of Science (BS) Computer Science, Bachelor of Science (BS) Computer Science at Massachusetts Institute of Technology
languagesThai, English, Chinese
github-logo-circle

Github Skills (7)

xla10
compiler-design10
c-language10
cprogramming-language10
operation10
linear-algebra10
hla10

Programming languages (4)

C++RustRacketJupyter Notebook

Github contributions (5)

github-logo-circle
openxla/xla

Jul 2020 - Jan 2023

A machine learning compiler for GPUs, CPUs, and ML accelerators
Role in this project:
userBack-end Developer
Contributions:26 commits in 2 years 6 months
Contributions summary:Phitchaya primarily contributed to improving the XLA compiler's functionality and robustness. They fixed fingerprint mismatch issues, ensuring deterministic behavior in the compilation process. They made code modifications related to memory usage tracking and instruction fusion, enhancing the efficiency of the compilation pipeline. Additionally, they implemented improvements for while loop bounds analysis and incorporated code for handling infeed/outfeed configurations.
compilercommunity-drivenmachine-learningmodular
mangpo/greenthumb

Feb 2014 - Jun 2022

Contributions:3 releases, 700 commits, 8 PRs in 8 years 5 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.
Request Free Trial
Phitchaya Phothilimthana - Member Of Technical Staff at OpenAI