Runxin He
Software Engineer Machine Learning Engineer at Airbnb
Austin, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolRunxin He is a Staff-level software and machine learning engineer with a decade of experience building AI/ML infrastructure and production systems across finance, autonomous driving, and enterprise platforms. Currently at Airbnb in Austin, he previously led end-to-end ML system design at Visa and contributed research-grade computer vision and optimal control work at Baidu USA. His open-source contributions include performance and planner improvements to the prominent Apollo autonomous driving platform, reflecting a focus on algorithm optimization and parallelization. Trained as a PhD in electrical engineering, he blends rigorous numerical and optimization expertise with pragmatic engineering to ship scalable, real-time and batch ML solutions. Notably, his background spans both supply-chain optimization and greenhouse AI that delivered measurable business impact, showing a proven ability to translate research into production value.
10 years of coding experience
14 years of employment as a software developer
BS Electronic Engineering, BS Electronic Engineering at Fudan UniversityDoctor of Philosophy (PhD) Electrical and Electronics Engineering, Doctor of Philosophy (PhD) Electrical and Electronics Engineering at Washington University in St. LouisThe Chinese University of Hong Kong (CUHK)
Chinese, English
Github Skills (6)
algorithm10
algorithms10
c-language10
cprogramming-language10
autonomous-driving10
parallel-computing9
Programming languages (2)
Github contributions (5)
ApolloAuto/apollo
Dec 2018 - Aug 2019
An open autonomous driving platform
Role in this project:
Back-end Developer
Back-end DeveloperContributions:62 commits, 74 PRs, 14 pushes in 7 months
Contributions summary:Runxin's commits focus on modifying and extending the Apollo autonomous driving platform, specifically within the planning module. They introduce and configure parameters for the Ipopt solver used in the distance approach algorithm. The user also refactors code to incorporate Ipopt configurations into various open-space planning modules, indicating involvement in algorithm optimization and system integration. Furthermore, the user parallelizes the reeds_shepp_path.cc file and adds parallel implementations to the open-space smoother, which implies performance improvement focus.
autonomous-drivingapolloautonomous-vehiclesautonomyself-driving-car
deidaraho/apollo
Dec 2018 - Sep 2019
An open autonomous driving platform
Contributions:8 PRs, 152 pushes, 15 branches in 9 months
autonomousmachine-learningautonomous-drivingmavlinkdriving
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.