Jesse Benson
Principal Software Engineering Manager at Microsoft
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolJesse Benson is a Principal Software Engineering Manager in Seattle with 11 years of experience building high-performance AI and cloud infrastructure at Microsoft, specializing in inferencing and hardware acceleration across CPUs, GPUs, FPGAs and the Maia AI chip. He leads host/device runtime teams for ONNX Runtime and has hands-on contributions enabling new execution providers and CPU feature optimizations for a widely used open-source ML runtime. His background spans distributed systems, device drivers, and end-to-end Azure services—bringing deep systems engineering from hyper-scale compute to serverless and IoT. Trained in computer architecture and accelerators at UW–Madison, he combines research-era insight (DySER) with production-grade delivery, and maintains a curiosity for space exploration that informs his appetite for complex, cross-disciplinary problems.
11 years of coding experience
5 years of employment as a software developer
M.S. Computer Engineering, M.S. Computer Engineering at University of Wisconsin-Madison
Github Skills (11)
machine-learning10
deeplearning-ai10
c-language10
deep-learning10
onnx10
cprogramming-language10
hardware-acceleration10
python9
cuda9
neural-network8
artificial-neural-networks8
Programming languages (9)
Github contributions (5)
microsoft/onnxruntime
Dec 2018 - May 2021
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
ML Engineer
ML EngineerContributions:68 reviews, 53 commits, 47 PRs in 2 years 5 months
Contributions summary:Jesse primarily contributed to the ONNX Runtime project by implementing and enhancing support for various execution providers, specifically focusing on hardware acceleration and machine learning inference. They added support for checking CPU features like F16C, which is crucial for optimizing performance on specific hardware. Additionally, the user updated and implemented new execution providers such as BrainSlice, including adding python APIs, showcasing their expertise in integrating different hardware acceleration backends. Furthermore, they made crucial updates to the existing kernels to improve performance.
runtimetrainingtensorflowai-frameworkaccelerator
jessebenson/azure-performance
Apr 2017 - Feb 2019
Contributions:133 commits, 129 pushes, 2 branches in 1 year 10 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.