Chen Xu
Frontend Engineer at Intel Corporation
California, United States
Summary
🤩
Rockstar🎓
Top SchoolChen Xu is a Frontend Engineer based in California with six years of engineering experience and a master's in Electrical, Electronics and Communications Engineering from Santa Clara University. Currently at Intel, Chen transitioned from a physical design intern—where he performed placement, routing and timing analysis for ASICs—to a frontend role blending systems thinking with performance-focused development. He is an active open-source contributor to the well-known OpenVINO toolkit, enhancing Reduce and Broadcast nodes for blocked layouts and fixing SSE41 issues to improve CPU inference performance and numerical accuracy. That mix of hardware-aware background and software performance engineering gives him a rare ability to optimize across the stack, from low-level instructions to high-level deployment in AI inference toolchains.
5 years of coding experience
1 year of employment as a software developer
Master's degree, Electrical, Electronics and Communications Engineering, Master's degree, Electrical, Electronics and Communications Engineering at Santa Clara University
Github Skills (5)
cpu-architecture10
c-language10
cprogramming-language10
performance-optimization10
linear-algebra9
Programming languages (1)
Github contributions (5)
openvinotoolkit/openvino
Sep 2020 - Dec 2022
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:524 reviews, 20 commits, 66 PRs in 2 years 3 months
Contributions summary:Chen's primary contribution involves extending the Reduce node within the OpenVINO toolkit to support blocked layouts, specifically for nC[d]hw8/16C formats on the CPU. They fixed an illegal instruction issue on SSE41 for the Reduce node and also optimized the Broadcast node for cases with scalar input. Additional work involved optimizing and adding support for the Reduce node, including dynamism support and performance improvements. They also appear to be involved in improving the performance and mathematical accuracy of the Reduce node.
inference-enginepytorchmodel-optimizerdeep-learninggpu
xuchen-intel/openvino
May 2020 - Mar 2025
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:3 PRs, 1188 pushes, 233 branches in 4 years 10 months
pytorchdeep-learningdeploymentopenvino-toolkitinference
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.