Marek Wydmuch

Machine Learning Researcher at Snowflake / Poznan University of Technology / ML in PL / Farama Foundation

Poland
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Marek Wydmuch is a machine learning researcher with 11 years of hands-on experience building and refining intelligent systems from backend to research code. Based in Greater Poland Voivodeship, he pairs academic rigor with pragmatic engineering, contributing bug fixes and feature improvements to high-profile open-source RL environments such as ViZDoom. His work touches low-level game state, camera and sound systems—areas that reveal an attention to reproducibility and realistic simulation critical for robust RL experiments. Marek blends research-oriented thinking with production sensibilities, making incremental but impactful contributions that keep complex codebases reliable. He is comfortable navigating both experimental prototypes and maintenance-heavy backend tasks, helping teams move from prototypes to usable research platforms. Colleagues value him for quietly improving developer experience and simulation fidelity in service of better ML outcomes.
code11 years of coding experience
github-logo-circle

Github Skills (7)

debugging10
c-language10
game-development10
cprogramming-language10
game-dev9
multiplayer-game9
multiplayer9

Programming languages (9)

TypeScriptC++ShellCTeXJavaScriptHTMLRuby

Github contributions (5)

github-logo-circle
Farama-Foundation/ViZDoom

Jun 2015 - Jan 2023

Reinforcement Learning environments based on the 1993 game Doom :godmode:
Role in this project:
userBack-end Developer
Contributions:34 releases, 44 reviews, 731 commits in 7 years 8 months
Contributions summary:Marek's contributions focused on fixing various issues within the ViZDoom codebase. The changes included updates to the view controls in spectator mode, fixing bugs related to the ammo in ClearInventory, and other fixes related to the player's game state and camera. The user has also made improvements to the sound and map control system.
reinforcement-learning-environmentsdeep-learningreinforcement-learningpythonvizdoom
mwydmuch/send_emails.py

Oct 2019 - May 2022

Contributions:10 commits, 8 pushes in 2 years 7 months
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