Jesse Farebrother
Ph.D. Student at Mila - Quebec Artificial Intelligence Institute
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolJesse Farebrother is a Ph.D. student at Mila researching AI and decision making with 13 years of engineering and research experience across industry leaders including Meta, Google DeepMind, and Google Brain. He blends rigorous academic training from McGill and the University of Alberta with hands-on systems work, contributing substantial backend and DevOps improvements to flagship open-source projects like OpenAI Gym and the Arcade Learning Environment. His contributions include modernizing C++ cores, migrating build systems to CMake and Python interfaces, and transitioning video rendering to SDL2—work that materially improved Atari RL environments used by the research community. Comfortable moving between low-level engineering and theoretical research, he has repeatedly operated at the intersection of reproducible RL infrastructure and novel decision-making algorithms. Based in London, he brings a rare combination of production-grade code stewardship and active research collaboration with leading ML labs.
13 years of coding experience
6 years of employment as a software developer
Bachelor of Science - BSc, Computer Science, Bachelor of Science - BSc, Computer Science at University of AlbertaDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at McGill University
Stackoverflow
1,199reputation
66kreached
14answers
10questions
Github Skills (21)
github-ci10
c-language10
python10
openai-gym10
cmake10
cicd10
build-automation10
cprogramming-language10
githubaction-workflow10
sdl9
reinforcement-learning9
pytest8
testing8
eclipse6
android-volley6
Programming languages (20)
Github contributions (5)
Farama-Foundation/Arcade-Learning-Environment
Sep 2019 - Sep 2022
The Arcade Learning Environment (ALE) -- a platform for AI research.
Role in this project:
Backend & DevOps Engineer
Backend & DevOps EngineerContributions:7 releases, 28 reviews, 150 commits in 2 years 11 months
Contributions summary:Jesse's commits primarily involved integrating and modernizing the codebase. Key contributions include incorporating C++ algorithms for the core display screen functions, centralizing version control through CMake, and migrating the build process to utilize a new Python interface. Additional contributions include significant refactoring of the source code, including the removal of deprecated components and the transition to SDL2 for enhanced video rendering. Finally, the user was also responsible for creating and maintaining build and deployment workflows.
arcade-learning-environmentarcadedeep-learningreinforcement-learningmachine-learning
openai/gym
Jun 2019 - Feb 2022
A toolkit for developing and comparing reinforcement learning algorithms.
Role in this project:Back-end Developer
Back-end DeveloperContributions:30 reviews, 17 commits, 17 PRs in 2 years 8 months
Contributions summary:Jesse primarily contributed to the Atari environment within the OpenAI Gym repository. Their work involved modifying the Atari environment, including updates to the `atari_env.py`, and integrating the official ALE Python package, as well as refactoring the `atari_preprocessing.py` and the test for frame stacking. They also modified the environment registration and tests to accommodate the changes related to Atari environments. Furthermore, the user addressed default parameters and overall structure of the Atari environments.
comparingreinforcement-learning-algorithmsdevelopingdeep-learningreinforcement-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.