Arash Pakbin is a systems-focused performance engineer with 8 years of experience who now optimizes PyTorch for AMD GPUs as a Performance Engineer (MTS) in the San Francisco Bay Area. Trained originally as an electrical engineer and holding advanced computer science degrees from Texas A&M, he specializes in CUDA/HIP kernel tuning, building PyTorch extensions, and integrating ML backends like MIOpen and hipBLASLt for large-scale workloads. His background includes practical speedups of I/O-bound Python pipelines at Tesla and early research in digital image forensics, reflecting a blend of low-level systems skills and applied ML tooling. An active contributor to the PyTorch ecosystem at AMD, he brings both academic rigor and hands-on production experience to squeezing performance from modern accelerators.
8 years of coding experience
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Texas A&M University
Bachelor of Science (B.Sc.), Electrical and Electronics Engineering, cumulative GPA: 3.88/4, Bachelor of Science (B.Sc.), Electrical and Electronics Engineering, cumulative GPA: 3.88/4 at University of Tehran
Diploma, Mathematics and Physics, Diploma, Mathematics and Physics at National Organization for Development of Exceptional Talents (Sampad)
Contributions:1 release, 21 pushes, 1 tag in 1 year 1 month
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
Arash Pakbin - PyTorch Performance Engineer (MTS) at AMD