Jeongseok Lee
Software Engineer at Meta
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolJeongseok Lee is a software engineer and robotics scientist with 13 years of experience building physics-driven simulation systems that enable sim-to-real transfer for humanoid robots and AR/VR avatars. At Meta he architects full-stack frameworks that combine physics engines, rendering, sensor simulation, and synthetic data to move models from virtual training into real-world deployment. He co-created and continues to lead development on DART, a widely used open-source dynamics and simulation library, and has contributed core optimizations to Bullet and infrastructure improvements to the Flexible Collision Library. His background spans academic research and industry—Georgia Tech, Carnegie Mellon, Amazon, and Meta—bridging multibody dynamics, motion planning, and machine learning to solve hard contact and control problems. Based in Seattle, he enjoys tackling cross-disciplinary challenges where low-level numerical solvers meet large-scale engineering and deployment.
13 years of coding experience
12 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at University of WashingtonDoctor of Philosophy - PhD candidate (ABD), Mechanical and Aerospace Engineering, Doctor of Philosophy - PhD candidate (ABD), Mechanical and Aerospace Engineering at Seoul National University
Korean, English
Github Skills (18)
c-language10
apidoc10
cmake10
travis-ci10
cicd10
api10
cprogramming-language10
software-design9
simulation9
simulations9
game-development9
kinematics8
animation7
git7
robotics7
Programming languages (9)
Github contributions (5)
flexible-collision-library/fcl
Mar 2015 - Mar 2018
Role in this project:
Backend & DevOps Engineer
Backend & DevOps EngineerContributions:3 releases, 391 commits, 149 PRs in 3 years
Contributions summary:Jeongseok primarily contributed to infrastructure setup and CI/CD pipeline improvements. The commits involve setting up Travis-CI for the project and configuring build and test processes for multiple operating systems (Linux and macOS). The user also reduced the sizes of tests in debug mode by changing the configurations of the testing tools.
collision-detectionmachine-learningcollisionpathfindingflexible
dartsim/dart
Apr 2013 - Jan 2023
DART: Dynamic Animation and Robotics Toolkit
Role in this project:Back-end Developer
Back-end DeveloperContributions:56 releases, 105 reviews, 4325 commits in 9 years 10 months
Contributions summary:Jeongseok's commits primarily focus on adding features and implementing backend logic, as demonstrated by the addition of new methods like `readAll()` to resources and retrievers. The code changes involve enhancements to the codebase, including adding a Factory class and collision detector factory. Further contributions involve adding functionality for joint force/torque retrieval.
kinematicsroboticsanimationcomputer-animationsimulation
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.