Jeff Bloomfield
Principal Software Engineer at Microsoft
Redmond, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolJeff Bloomfield is a Principal Software Engineer at Microsoft with over 8 years of focused engineering experience and a long tenure at the company dating back to 2004. He brings deep backend and DevOps expertise, notably contributing to Microsoft’s ONNX Runtime by improving the DirectML execution provider, fixing complex kernel issues, and adding shape inference for ConvTransposeWithDynamicPads. Based in Redmond and trained at Carnegie Mellon in Electrical and Computer Engineering, he blends systems-level rigor with practical performance and code-quality improvements. Colleagues rely on him for resolving subtle inferencing failures and optimizing external weight handling in ML runtimes. He pairs production-focused problem solving with open-source collaboration on a high-profile project used broadly in ML inference and training.
8 years of coding experience
BS, Electrical and Computer Engineering, BS, Electrical and Computer Engineering at Carnegie Mellon University
Github Skills (11)
deeplearning-ai10
c-language10
deep-learning10
onnx10
cprogramming-language10
directml10
artificial-neural-networks9
neural-network9
hardware-acceleration9
machine-learning9
python4
Programming languages (3)
Github contributions (5)
microsoft/onnxruntime
Oct 2019 - Nov 2022
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
Back-end & DevOps Engineer
Back-end & DevOps EngineerContributions:113 reviews, 117 commits, 85 PRs in 3 years 2 months
Contributions summary:Jeff primarily worked on enhancing the DML (DirectML) execution provider within the ONNX Runtime. Their contributions focused on fixing issues with DML kernels, including resolving failures related to DML RNN and fixing kernel registry validation. They also implemented the addition of shape inference for the ConvTransposeWithDynamicPads schema and extended DML kernels, addressing various aspects of code quality. Furthermore, the user addressed performance issues and improved the code related to external weights.
runtimetrainingtensorflowai-frameworkaccelerator
jeffbloo/onnx
May 2018 - May 2018
Open Neural Network Exchange
Contributions:25 pushes, 5 branches in 26 days
exchangecaffe2machine-learningcaffeneural-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.