Andrew Tan
Software Engineer at Swarmlabs
Singapore, Singapore
Summary
👤
Senior🎓
Top SchoolAndrew Tan is a software engineer and founding engineer at Swarm Labs with eight years of experience building AI and cybersecurity products, combining full-stack development with machine learning expertise. He previously optimized large-scale ad ranking and core deep learning models at Shopee and has hands-on research experience in quantum software and NLP from stints at Entropica Labs and A*STAR. A National University of Singapore CS graduate who also spent time at Georgia Tech, he excels at shipping scalable evaluation systems and has led rendering-focused contributions to high-profile open-source RL projects like OpenAI Gym and PettingZoo. Known for pragmatic refactors—e.g., replacing pyglet with pygame to improve maintainability and fix edge-case rendering—he bridges research and production to make complex algorithms operational. Based in Singapore, he brings a rare blend of algorithmic curiosity and product-oriented engineering to startup and platform-scale challenges.
8 years of coding experience
3 years of employment as a software developer
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Georgia Institute of TechnologyBachelor's degree Computer Science Major | Physics Minor, Bachelor's degree Computer Science Major | Physics Minor at National University of Singapore
Github Skills (12)
gymnasium10
openai-gym10
refactoring10
pygame10
multi-agent-reinforcement-learning10
render10
box2d10
python10
rendering10
game-development9
api9
reinforcement-learning8
Programming languages (3)
Github contributions (5)
openai/gym
Dec 2021 - May 2022
A toolkit for developing and comparing reinforcement learning algorithms.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:11 reviews, 10 commits, 9 PRs in 5 months
Contributions summary:Andrew refactored several environments within the OpenAI Gym repository to utilize Pygame for rendering, specifically focusing on the Box2D environments like Lunar Lander, Bipedal Walker, and Car Racing. Their contributions included updating the rendering logic, optimizing performance, and fixing display issues. Additionally, the user addressed edge cases in the Car Racing environment, fixing out-of-bounds rendering issues. They also made improvements to event handling for human mode rendering.
comparingreinforcement-learning-algorithmsdevelopingdeep-learningreinforcement-learning
Farama-Foundation/PettingZoo
Dec 2021 - Oct 2022
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:7 commits, 4 PRs, 1 comment in 9 months
Contributions summary:Andrew primarily worked on refactoring and adapting existing code to use pygame for rendering within the multiwalker environment, replacing the previous pyglet dependency. They also suppressed pygame import messages in multiple files, and fixed import statements. The user modified and updated various environment files, demonstrating an understanding of the overall structure and rendering components of the pettingzoo project. These changes suggest a focus on improving the environment's visual presentation and maintainability.
agentreinforcement-learningreinforcement-learning-agentgymnasiumdeep-reinforcement-learning
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.