Chris Sullivan
Principal Engineer at NVIDIA
Beaverton, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolChris Sullivan is a Principal Engineer at NVIDIA with 11 years of experience blending high-performance computing, deep learning compilers, and nuclear astrophysics research. He holds dual Ph.D. training in Physics and Computational Mathematics and brings uncommon domain depth—spokesperson for two nuclear experiments and a background in core-collapse supernova simulations—into GPU and compiler engineering. At NVIDIA (and previously OctoAI/Habana/Intel) he has driven backend ML compiler work (notably contributions to the popular TVM stack for TensorFlow and ONNX importers) and led performance engineering for accelerators. He routinely bridges scientific modeling and production-grade systems, pursuing formal HPC certification while shipping optimizations for GPUs and distributed workloads. Based in Beaverton, he mixes academic rigor with product-focused leadership, making him effective at translating complex physics uncertainty analyses into scalable software solutions.
11 years of coding experience
10 years of employment as a software developer
Bachelor of Science (BS) Physics, Bachelor of Science (BS) Physics at Westmont CollegeDoctor of Philosophy - PhD Dual: Physics & Computational Mathematics Science and Engineering, Doctor of Philosophy - PhD Dual: Physics & Computational Mathematics Science and Engineering at Michigan State University
Stackoverflow
214reputation
24kreached
6answers
10questions
Github Skills (17)
tvm10
relay-modern10
onnx10
relay10
python9
machine-learning9
compiler-compiler9
deep-learning9
compiler9
google-ads-api6
boost6
capybara6
serialization6
ruby6
boost-serialization6
Programming languages (5)
Github contributions (5)
apache/tvm
Jul 2020 - Nov 2022
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:421 reviews, 38 commits, 139 PRs in 2 years 4 months
Contributions summary:Chris contributed to the Relay and TVM compiler stack, specifically focusing on TensorFlow integration. They implemented support for the NonMaxSuppressionV4 operation in TensorFlow, enabling its ingestion by the TVM compiler. Additionally, the user made improvements to the ONNX slice converter, updating it to correctly infer slice attributes. Furthermore, they added the Clip importer to handle cases when min/max were provided as inputs.
metalvulkancompilertensoropencl
csullivan/Entendre
Sep 2016 - Dec 2020
Contributions:10 PRs, 9 pushes, 2 branches in 4 years 4 months
implementationsdeep-learningneural-networksmachine-learningneural-network
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.