Chris Leary
Member Of Technical Staff at OpenAI
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolChris Leary is a systems-and-compilers engineer with 17 years of experience building co-designed software and hardware tooling, currently a Member of Technical Staff at OpenAI and formerly a Senior Staff Software Engineer at Google. He founded the open-source XLS project for accelerated hardware synthesis and was a founding tech lead on XLA, driving compiler, runtime, and ISA co-design for TPUv2/v3 and establishing StreamExecutor for heterogeneous accelerators. His work spans low-level compilers, ISAs, hardware tools, and full-stack codesign—contributing substantive bytecode and control-flow features to DSLX and improving RCX extraction and XLA correctness across major open-source repos. Based in Mountain View, he combines deep production experience at Google and NVIDIA with early compiler research from Mozilla and Cornell, making him adept at both algorithmic rigor and engineering pragmatism. A subtle through-line in his career is quietly elevating code quality and maintainability—refactoring, smart-pointer modernizations, and targeted bug fixes that enable long-lived infrastructure.
17 years of coding experience
15 years of employment as a software developer
B.S. Electrical and Computer Engineering Computer Science, B.S. Electrical and Computer Engineering Computer Science at Cornell UniversityComputer Science, Computer Science at Stanford University
Stackoverflow
70,492reputation
10.8mreached
118answers
90questions
logging
top-5%
list-comprehension
top-1%
javascript
top-5%
subprocess
top-5%
django
top-5%
serialization
top-5%
Github Skills (39)
c-language10
python10
list-comprehension10
testing10
interpreter10
eda10
compiler-design10
computer-engineering10
bytecode10
rt10
xla10
compiler10
cpp10
cprogramming-language10
type-check9
Programming languages (8)
Github contributions (5)
google/xls
May 2020 - Jan 2023
XLS: Accelerated HW Synthesis
Role in this project:
Back-end Developer
Back-end DeveloperContributions:128 reviews, 618 commits, 177 PRs in 2 years 8 months
Contributions summary:Chris made significant contributions to the DSLX (Domain-Specific Language for eXtreme-scale hardware) compiler project. They primarily focused on implementing new functionalities and features for the bytecode interpreter including introducing the `DUP` instruction, and adding support for the `for` and `ternary` control flow constructs. Their work included modifications to the code generator and type-checker, as well as supporting new features within the compiler framework.
high-level-synthesisxlsacceleratedsynthesiscompiler
openxla/xla
Jul 2017 - Feb 2019
A machine learning compiler for GPUs, CPUs, and ML accelerators
Role in this project:Back-end Developer
Back-end DeveloperContributions:70 commits in 1 year 7 months
Contributions summary:Chris primarily focused on bug fixes and improvements within the XLA compiler, specifically addressing issues related to outfeed and call inlining functionalities. Their work involved modifying and testing core XLA service files, including those related to instruction cloning, computation inlining, and CPU transfer management. The commits show a strong involvement in enhancing the compiler's correctness, performance, and stability, focusing on low-level details of the XLA compiler's behavior.
compilercommunity-drivenmachine-learningmodular
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.