Rahul Garg
Senior MTS, GPU Performance Application Machine Learning Engineer
California, United States
Summary
🤩
Rockstar🎓
Top SchoolRahul Garg is a Senior MTS and GPU Performance Application/Machine Learning Engineer at AMD with over a decade of experience building high-performance, heterogeneous computing solutions. He specializes in GPU and multi-core programming, HIP/ROCm portability for CUDA-to-AMD migration, and applying ML/recommendation techniques to performance problems while also managing AWS infrastructure. His background spans mobile multimedia, codecs and streaming protocols, big-data performance tuning, and low-level benchmarking and microarchitecture-aware optimization. Rahul has led teams and products at Samsung and co-founded a startup, pairing hands-on engineering with project and requirement management skills. An active open-source contributor, he works directly on HIP and related ROCm tooling, bridging research-grade algorithms and production GPU performance engineering. Based in California and trained at IIT Delhi, he blends systems-level depth with practical delivery across embedded, server, and cloud environments.
10 years of coding experience
10 years of employment as a software developer
Indian Institute of Technology Delhi (IIT Delhi)
Github Skills (53)
opencl10
pytorch10
python10
ocr10
gpu-programming10
machine-learning10
blas10
amd10
hip10
lstm10
deep-learning10
gpu10
natural-language-processing10
tesseract10
cuda10
Programming languages (5)
Github contributions (5)
gargrahul/HIP
Dec 2017 - Feb 2022
HIP : Convert CUDA to Portable C++ Code
Contributions:201 commits, 325 pushes, 192 branches in 4 years 2 months
cudacppgpuc-plus-plusportable
ROCm/MAD
Jul 2024 - Apr 2025
Contributions:11 reviews, 36 PRs, 23 pushes in 8 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.