Michael Kuperstein
Staff Software Engineer at Google
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolMichael Kuperstein is a Staff Software Engineer with 10+ years of R&D experience specializing in compilers, program analysis, and performance engineering for CPUs, GPUs and ML accelerators. He has driven compiler optimizations and backend work across Google, Intel, and Waymo—contributing notably to XLA’s dataflow analysis for machine learning accelerators and real-world Clang/LLVM optimization efforts. Comfortable across concurrent algorithms, distributed systems, and cloud networking, he blends deep systems-level expertise with practical production impact. Based in New York, he brings a research-minded approach from an M.Sc. at Technion and a track record of improving compiler correctness and performance rather than chasing flashy titles.
10 years of coding experience
20 years of employment as a software developer
M.Sc Computer Science, M.Sc Computer Science at Technion - Israel Institute of TechnologyB.Sc. Computer Science, B.Sc. Computer Science at Tel Aviv University
English, Hebrew, Russian
Github Skills (6)
xla10
c-language10
cprogramming-language10
dataflow10
testing9
compiler-optimization9
Programming languages (5)
Github contributions (5)
openxla/xla
Feb 2018 - Jan 2023
A machine learning compiler for GPUs, CPUs, and ML accelerators
Role in this project:
Back-end Developer
Back-end DeveloperContributions:100 commits, 1 comment in 4 years 11 months
Contributions summary:Michael primarily contributed to the XLA compiler, focusing on dataflow analysis and its related components. Their commits involved modifying the `HloDataflowAnalysis` class, related header files, and test files, demonstrating a focus on improving the compiler's internal workings. They also added and enhanced tests for slice operations, addressing potential performance and memory-related issues. Additionally, they addressed potential runtime issues in the heap simulator.
compilermachine-learning
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.