Sanghyun Son
Technical Staff at Genesis AI
San Carlos, California, United States
Summary
👤
Senior🎓
Top SchoolSanghyun Son is a Technical Staff engineer and incoming industry researcher with nine years of engineering experience and a PhD in progress from the University of Maryland, where he worked at GAMMA Lab under Ming C. Lin on projects at the intersection of geometry, physics, and reinforcement learning. He has interned twice at Adobe and transitioned from a research intern to Technical Staff at Genesis AI, bringing research-grade modeling and systems experience into production contexts. An active open-source contributor, he fixed subtle bugs and extended environments in the widely-used PettingZoo multi-agent RL library, including Go and Texas Hold'em integrations. Based in San Carlos, CA, he blends deep theoretical grounding with pragmatic backend engineering, often surfacing and resolving hard-to-reproduce simulation and rendering issues.
9 years of coding experience
1 year of employment as a software developer
석사 컴퓨터 과학, 석사 컴퓨터 과학 at Seoul National UniversityDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Maryland
Github Skills (7)
multi-agent-reinforcement-learning10
python10
reinforcement-learning10
api9
gymnasium9
go8
numpy7
Programming languages (3)
Github contributions (5)
Farama-Foundation/PettingZoo
Jul 2021 - Nov 2021
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 review, 7 commits, 3 PRs in 4 months
Contributions summary:Sanghyun primarily contributed to the `pettingzoo` repository by addressing bugs and updating existing environments. Their work involved fixing go encoding errors and go board rendering bugs within the Go environment. Additionally, they updated and integrated the Texas Hold'em no-limit environment, updating dependencies and metadata. They also resolved a teleportation bug in a cooperative pong environment.
agentreinforcement-learningreinforcement-learning-agentgymnasiumdeep-reinforcement-learning
SonSang/DiffRL
Dec 2022 - Feb 2023
[ICLR 2022] Accelerated Policy Learning with Parallel Differentiable Simulation
Contributions:49 commits, 80 pushes, 7 branches in 1 month
policyiclrdifferentiableparallelaccelerated
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.