Jordan Terry
Founder & CEO at Farama Foundation
Washington, District of Columbia, United States
Summary
🤩
Rockstar🎓
Top SchoolJordan Terry is the founder and CEO of the Farama Foundation, stewarding open-source reinforcement learning infrastructure used by every major AI research lab and totaling 250+ million installations. A former startup founder of Swarm Labs and an ML lead in defense and neuromorphic startups, she combines product-grade engineering with security-conscious AI tooling and has guided projects into late-stage acquisition talks. Her PhD work at the University of Maryland produced industry-standard RL interfaces and novel methods for modeling chaotic and economic systems, reflecting a strong physics-to-AI research lineage. Jordan is a hands-on contributor to flagship projects like OpenAI Gym and PettingZoo, focusing on build reliability, multi-agent APIs, and reproducible training workflows. Based in Washington, D.C., she bridges academic rigor and production-scale open-source stewardship, with a knack for turning research prototypes into infrastructure relied upon by cloud providers and labs. An underappreciated detail: her background in precision experimental physics informs pragmatic system design choices that improve stability in complex RL tooling.
10 years of coding experience
8 years of employment as a software developer
PhD Computer Science, PhD Computer Science at University of Maryland
Github Skills (35)
pytorch10
py10
python10
image-processing10
setuptools10
machine-learning10
multi-agent10
scikit-image10
travis-ci10
reinforcement-learning10
cicd10
numpy10
hyperparameter-optimization10
deeplearning-ai10
deep-learning10
Programming languages (13)
Github contributions (5)
openai/gym
Nov 2020 - Jan 2023
A toolkit for developing and comparing reinforcement learning algorithms.
Role in this project:
DevOps Engineer & Python Developer
DevOps Engineer & Python DeveloperContributions:16 releases, 7 reviews, 161 commits in 2 years 2 months
Contributions summary:Jordan focused on maintaining the project's infrastructure and build processes. This included removing Python 3.5 support, updating Travis CI configurations, and integrating necessary dependencies for testing. The user also addressed setup.py maintenance and Python 3.9 support, demonstrating a focus on environment compatibility and build system management within the reinforcement learning environment.
reinforcement-learning
Farama-Foundation/PettingZoo
Jan 2020 - Oct 2022
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Role in this project:Backend Developer
Backend DeveloperContributions:6 releases, 55 reviews, 1488 commits in 2 years 9 months
Contributions summary:Jordan focused on implementing and refining the core mechanics of the Pistonball environment. Their commits centered around fixing action-taking, defining the discrete action space, and providing clear error messages to help guide developers. These changes improved the game's functionality and user experience. In addition, the user made formatting and style changes to improve the readability of the source code.
multi-agent-reinforcement-learningapigymnasiumreinforcement-learningmultiagent-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.