Xinyu Wang
Software Engineer at Microsoft
Tokyo, China
Summary
🤩
Rockstar🎓
Top SchoolXinyu Wang is a software engineer specializing in robotics, deep learning, and high-performance computing, with four years of experience building perception and planning systems for autonomous vehicles. He has contributed to Autoware.Universe by enhancing mission planning, shape estimation, and integrating a CenterPoint TVM package, reflecting hands-on work at the intersection of ML and compiler/optimization stacks. Former roles include software architect at TIER IV and research-focused engineering on Lidar–IMU SLAM at ZMP, demonstrating a strong background in mapping, optimization, and systems design. Now at Microsoft, he brings applied research experience from UCLA and practical industry internships (including Baidu) to production-grade robotics software. Known on GitHub as "Vege Dog," he combines curiosity-driven open-source contributions with pragmatic engineering for real-world autonomy.
4 years of coding experience
4 years of employment as a software developer
Bachelor's degree Electrical and Electronics Engineering, Bachelor's degree Electrical and Electronics Engineering at UC San Diego Jacobs School of EngineeringUniversity of California, Los Angeles
Github Skills (13)
c-language10
planning10
missionplanner10
cprogramming-language10
self-driving-car10
ros10
autonomous-driving10
python9
tvm9
machine-learning8
3d-mapping8
tensorflow7
calibration6
Programming languages (5)
Github contributions (5)
autowarefoundation/autoware_universe
Apr 2022 - Jan 2023
Role in this project:
Back-end & ML Engineer
Back-end & ML EngineerContributions:44 reviews, 14 commits, 40 PRs in 9 months
Contributions summary:Xinyu primarily contributed to the Autoware.Universe project by implementing and modifying planning and perception modules, specifically focusing on mission planning and shape estimation. Their work included aligning goal poses within a lanelet map and adding a boost optimizer for bounding box shape estimation. They also worked on optimizing interpolation methods within the obstacle avoidance planner. Furthermore, the user added and integrated centerpoint tvm package.
autowareros23d-mapcalibrationros
angry-crab/autoware.universe
Jan 2022 - Apr 2023
Contributions:94 pushes, 28 branches in 1 year 3 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.