Michael Iovine
Senior Software Engineer at NVIDIA
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolMichael Iovine is a Senior Software Engineer based in New York with 11 years of experience building high-performance ML inference systems and production runtimes. He has driven backend optimizations at Meta—contributing to the PyTorch Static Runtime used in ads ranking—and more recently to AITemplate, and now works on performance-focused engineering at NVIDIA. As a founding engineer at HippoML he bridged early product development with scalable model serving, demonstrating both startup agility and large-scale production experience. His open-source contributions to PyTorch’s static runtime show deep expertise in code generation, memory management, and execution pipelines that tangibly improved inference performance. Trained at Caltech in computer science with a data science minor, he combines rigorous academic foundations with hands-on systems engineering. He’s known for quietly tackling knotty runtime bugs and turning low-level fixes into measurable speedups.
11 years of coding experience
3 years of employment as a software developer
California Institute of Technology
Github Skills (14)
memory-management10
pytorch10
code-generation10
c-language10
tensor10
cprogramming-language10
python10
deeplearning-ai9
machine-learning9
neural-network9
debug9
deep-learning9
debugging9
autograd8
Programming languages (2)
Github contributions (5)
pytorch/pytorch
Jul 2021 - Nov 2022
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
Back-end Developer
Back-end DeveloperContributions:39 reviews, 228 commits, 162 PRs in 1 year 4 months
Contributions summary:Michael primarily contributed to the static runtime component of PyTorch, focusing on optimizing and fixing issues within the code generation and execution pipeline. They addressed memory management problems, improved schema checks for various operations, and added features like constant folding and improved handling of specific data structures. The user also implemented bug fixes in the JIT interpreter and made improvements to how the static runtime handles certain operations, resulting in performance enhancements.
pythongpu-accelerationdeep-learninggpunumpy
mikeiovine/vimrc
Dec 2019 - Mar 2025
Contributions:152 pushes, 1 branch in 5 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.