Ryan Neph
Senior Software Engineer at Google
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolRyan Neph is a Senior Software Engineer in Mountain View with 11 years of experience applying computer graphics, GPU programming, and deep learning to real-world problems across Chrome OS research and Google Health. He holds a PhD at the intersection of physics, biology, and machine learning where he developed large-scale convex optimization and imaging solutions for radiation therapy and tumor detection. At Google he bridges systems and research, shipping GPU-accelerated algorithms and vision models; earlier work at Siemens combined signal processing, NVH testing, and bespoke analysis software. An active open-source contributor, he implemented and optimized GPU kernels for tinygrad to bring PyTorch-like functionality to lightweight ML runtimes. His background in mechanical and engineering physics (3.91 GPA) gives him an uncommon blend of hardware intuition and numerical rigor that informs both low-level kernel tuning and high-level model design.
10 years of coding experience
10 years of employment as a software developer
Bachelor of Science - BS, Mechanical Engineering, 3.91, Bachelor of Science - BS, Mechanical Engineering, 3.91 at Kettering UniversityDoctor of Philosophy (Ph.D.), Physics and Biology in Medicine (Biomedical Physics), 3.99, Doctor of Philosophy (Ph.D.), Physics and Biology in Medicine (Biomedical Physics), 3.99 at University of California, Los Angeles
Github Skills (5)
opencl10
gpu-programming10
machine-learning10
python10
numpy9
Programming languages (7)
Github contributions (5)
tinygrad/tinygrad
Nov 2020 - Nov 2020
You like pytorch? You like micrograd? You love tinygrad! ❤️
Role in this project:
ML Engineer
ML EngineerContributions:6 reviews, 13 commits, 16 PRs in 7 days
Contributions summary:Ryan primarily contributed to the GPU acceleration of operations within the tinygrad framework, a project aiming to provide a PyTorch-like experience. Their work involved implementing and optimizing GPU kernels for various functions such as `pow`, `div`, `AvgPool2D`, and `MaxPool2D`, along with the necessary backward passes. Furthermore, the user addressed GPU selection and compatibility issues, ensuring the framework functions correctly across various GPU environments. The user's contributions also include strided pool functions.
deep-learningpytorchmicrograd
ryanneph/PyViz
Jun 2016 - Aug 2018
Contributions:30 commits, 20 pushes, 1 branch in 2 years 3 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.