Sudheer Chunduri
Software Engineer at Google
Sunnyvale, California, United States
Summary
👤
Senior🎓
Top SchoolSudheer Chunduri is a software engineer with 13 years of experience specializing in high-performance computing, systems performance modeling, and interconnect analysis, currently at Google in Sunnyvale. He has driven Exascale co-design efforts at Argonne National Laboratory, built low-overhead MPI and GPU profiling tools, and contributed optimizations that improved real-application performance and reduced network congestion across major HPC centers. His work spans analytical and discrete-event simulation, large-scale performance monitoring, and practical tuning of MPI implementations—highlighted by bug fixes and test-suite contributions to the official MPICH repository. Comfortable collaborating with vendors and application teams under tight deadlines, he has helped machine acceptance for top-10 supercomputers and implemented MPICH support for AMD GPUs destined for Frontier. Known for turning deep research into deployable tooling, he blends academic rigor from a PhD with hands-on systems engineering at national labs and industry.
13 years of coding experience
11 years of employment as a software developer
Master of Technology - MTech, Computer Science, Master of Technology - MTech, Computer Science at Sri Sathya Sai Institute of Higher Learning
Github Skills (7)
c1710
mpi10
hpc10
c1110
test-automation10
testing10
fortran9
Programming languages (3)
Github contributions (5)
pmodels/mpich
Aug 2018 - Jul 2022
Official MPICH Repository
Role in this project:
Backend & Test Automation Engineer
Backend & Test Automation EngineerContributions:13 reviews, 41 commits, 18 PRs in 3 years 11 months
Contributions summary:Sudheer primarily focused on improving the MPICH library through code enhancements and testing. Their contributions involved fixing integer overflows within the `MPI_Bcast` implementation. Additionally, the user modified the `recvq` event registration to include both rank and tag information, enhancing debugging capabilities. The user also developed and integrated a test suite to validate the `recvq` unexpected message MPI_T events.
fortranhpcmpic
argonne-lcf/autoperf
Aug 2019 - Jun 2022
Core autoperf source
Contributions:3 reviews, 79 commits, 19 PRs in 2 years 11 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.