Rati Devidze
Saarbrücken, Saarland, Germany
Summary
👤
Senior🎓
Top SchoolRati Devidze is an RL/ML engineer and PhD-trained researcher with eight years of experience bridging theoretical reinforcement learning and practical robotics/AI applications. Trained at Max Planck Institute for Software Systems and Universität des Saarlandes, he has published in top venues and focuses on designing informative, explicable reward functions to make RL agents more interpretable and reliable. He combines deep academic rigor with industry experience from startup and enterprise roles, currently applying his expertise at minds.ai. Known for tackling real-world decision-making problems, he brings both low-level implementation skills and a strong grounding in algorithmic research.
8 years of coding experience
6 years of employment as a software developer
Language and Ocupation training, Language and Ocupation training at FH Aachen University of Applied SciencesDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Max Planck Institute for Software Systems: MPI SWSCraduate Student Computer Science, Craduate Student Computer Science at Universität des SaarlandesBachelor's degree Computer Science, Bachelor's degree Computer Science at Tbilisi State University
English, German, Russian, Georgian
Github Skills (6)
statistics8
python8
data-science7
data-analysis7
machine-learning7
scikit-learn5
Programming languages (2)
Github contributions (5)
ratidevidze/ratidevidze.github.io
Feb 2018 - Mar 2026
About me
Contributions:95 pushes, 1 branch in 8 years 2 months
adishs/neurips2021_explicable-reward-design_code
Oct 2021 - Oct 2021
Contributions:11 commits in 2 days
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.