Ivan Berg

Redmond, Washington, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Ivan Berg is a senior developer at Microsoft with nine years of experience specializing in client and cloud performance debugging. He focuses on making complex systems observable and performant, recently enhancing profiling and logging for the QNN Execution Provider in the widely used ONNX Runtime to produce CSV-ready profiling output for easier analysis. Based in Redmond, he brings practical expertise in back-end performance engineering across large-scale ML inferencing infrastructure. Colleagues rely on him to translate noisy performance signals into actionable diagnostics, and he pairs deep technical troubleshooting with an eye for tooling that speeds root-cause analysis.
code9 years of coding experience
bookMontana State University-Bozeman
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (8)

c-language10
cprogramming-language10
profiling10
onnx9
hardware-acceleration9
csv9
machine-learning9
deep-learning9

Programming languages (5)

C#TypeScriptC++ShellPython

Github contributions (5)

github-logo-circle
microsoft/onnxruntime

Sep 2022 - Jan 2025

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
userBack-end Developer
Contributions:40 reviews, 24 PRs, 30 pushes in 2 years 4 months
Contributions summary:Ivan implemented changes to the QNN Execution Provider within the ONNX Runtime, focusing on enhancements for profiling and logging of events. They modified the QNN backend manager to output profiling logs to a CSV file, enabling easier interpretation of performance data. The code changes involved adding functionalities for extracting and formatting profiling event information. These modifications aimed to improve the diagnosability and performance analysis of the QNN execution provider within the ONNX Runtime framework.
runtimetrainingtensorflowai-frameworkaccelerator
ivberg/onnxruntime

Mar 2023 - Nov 2024

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Contributions:82 pushes, 13 branches in 1 year 8 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.
Request Free Trial
Ivan Berg