Eric Chen - Software Engineer at Waymo

Eric Chen

Software Engineer at Waymo

Sunnyvale, California, United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Eric Chen is a software engineer with nine years of experience building high-performance robotics and distributed ML systems from research prototypes to product-scale infrastructure. Currently at Waymo, he focuses on motion generation and trajectory initialization for autonomous pickups and drop-offs, drawing on prior work at Google on large-scale distributed pipelines for store visits estimation. His open-source contributions include low-level C++/CUDA work on a header-only differentiable physics simulator and backend refactors for the reinforcement learning toolkit Garage, showing a blend of numerical performance tuning and ML systems design. Earlier robotics research and internships at DJI and an academic lab produced practical perception, planning, and multi-drone systems, plus a habit of shipping demos and tooling. Comfortable across C++, CUDA, Python, and distributed systems, he often bridges research ideas and production constraints. A not-obvious strength: he repeatedly moves projects from prototype demos into reusable infrastructure, whether for academic robotics or production log processing.

9 years of coding experience

5 years of employment as a software developer

Bachelor of Science (B.S.), Computer Engineering and Computer Science, Bachelor of Science (B.S.), Computer Engineering and Computer Science at University of Southern California

High school, High school at Shenzhen Middle School

English, Chinese

Github Skills (22)

algorithm10

simulation10

code-optimization10

algorithms10

rep10

c-language10

robotics10

python10

simulator10

simulations10

physics10

repr10

optimisation10

cuda10

numerical-optimization10

Programming languages (2)

C++Python

Github contributions (5)

rlworkgroup/garage

May 2020 - Aug 2020

A toolkit for reproducible reinforcement learning research.

Role in this project:

Backend Developer

Contributions:3 reviews, 20 commits, 28 PRs in 3 months

Contributions summary:Eric primarily contributed to the backend of the `garage` repository, specifically focusing on refactoring and improving existing algorithms. They removed an iteration variable from the `optimize_policy` method within several algorithm implementations like `TD3`, `DDPG`, and `SAC`, likely improving code clarity and potentially performance. They also implemented changes to support Pybullet environments, including adding and adapting `BulletEnv`. Further contributions included code updates to incorporate `TimeStepBatch` and `EnvStep` as well as modifying existing functionality related to the environment class to align with best practices.

reinforcement-learningrl-algorithmsreproducibilitypytorchtensorflow

erwincoumans/tiny-differentiable-simulator

Jan 2021 - Feb 2021

Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

Role in this project:

Backend Developer

Contributions:11 commits, 7 PRs, 4 comments in 1 month

Contributions summary:Eric added core functionality related to a differentiable physics simulator. Contributions include implementing a SimpleRobot class, a COMVelocityEstimator, and an OpenloopGaitGenerator, which suggests the development of kinematic and dynamic control elements. Further work focused on integrating these components within a simulation environment using header-only C++ and CUDA, indicating a focus on performance and numerical computation. Additional commits added features related to a swing controller, further enhancing the robot's control capabilities.

cppcudareinforcement-learningroboticszero-dependencies

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