Rodrigo P

Washington DC-Baltimore Area United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Rodrigo P is a robotics and reinforcement learning software engineer with about six years of experience and over four years focused specifically on RL and robotics tooling. He currently contributes to Farama Foundation, helping standardize open-source RL environments and improve developer workflows, and has hands-on experience with influential projects like OpenAI Gym and PettingZoo. His strengths span backend development, QA/test automation, and DevOps—having modernized CI/CD, Docker builds, and type-hardened codebases for MiniGrid and MiniWorld environments. Rodrigo’s work often centers on making complex simulation environments reliable and testable (e.g., MuJoCo bindings, state APIs, and environment checks), a detail that underpins reproducible research in RL. He holds engineering degrees from Universidad Pontificia Comillas and an M.Eng. in Robotics from the University of Maryland, combining strong academic training with practical open-source impact.

6 years of coding experience

Bachelor of Science, Electromechanical Engineering, Bachelor of Science, Electromechanical Engineering at Universidad Pontificia Comillas

Master of Engineering, Robotics, Master of Engineering, Robotics at University of Maryland

Spanish, English

Github Skills (17)

github-ci10

docker10

pytest10

python10

testing10

gymnasium10

openai-gym10

dockers10

reinforcement-learning10

cicd10

mujoco10

githubaction-workflow10

multi-agent-reinforcement-learning9

typehinting9

type-checking9

Programming languages (5)

C++CHTMLJupyter NotebookPython

Github contributions (5)

Farama-Foundation/Minigrid

Jul 2022 - Jan 2023

Simple and easily configurable grid world environments for reinforcement learning

Role in this project:

DevOps Engineer & Software Engineer

Contributions:8 releases, 25 reviews, 69 commits in 6 months

Contributions summary:Rodrigo was instrumental in setting up and maintaining the CI/CD pipeline using GitHub Actions and Docker. They removed legacy build systems like Travis, integrated pre-commit hooks, and implemented testing infrastructure with pytest. The user also made significant contributions to code quality by incorporating type hints and addressing type-related errors. Their work also involved environment configuration, including the creation of a Dockerfile.

grid-worldconfigurablereinforcement-learningdeep-reinforcement-learningreinforcement

Farama-Foundation/PettingZoo

Feb 2021 - Jan 2023

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Role in this project:

Backend Developer & QA Engineer

Contributions:6 reviews, 84 commits, 19 PRs in 1 year 11 months

Contributions summary:Rodrigo primarily focused on adding and improving state-related functionalities within various environments, specifically targeting the "butterfly" environments within the `pettingzoo` library. They implemented `.state()` and `.state_space` methods, and wrote tests to ensure the correctness of these methods. This includes creating state tests and debugging identified issues in these environments, indicating a focus on both backend and testing.

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.

Request Free Trial