Sven Mika
Principal Software Engineer at Helsing
Germany
Summary
🤩
Rockstar🎓
Top SchoolSven Mika is an AI software engineer and reinforcement learning specialist with over a decade of hands-on experience building production-grade RL systems and leading teams. He was tech lead for Ray RLlib at Anyscale, guiding a team of RL engineers and contributing fixes and documentation to DreamerV3 and other core RLlib components used by major companies like Microsoft, Amazon and TwoSigma. Sven also authors open-source RL tooling—contributions to Tensorforce and his Surreal framework highlight his focus on integrating RL with complex simulators such as Unreal Engine for game and research use cases. His background spans quantitative trading systems and academic ML research (Columbia), giving him rare fluency across low-latency production software, scalable distributed ML, and foundational algorithms. Based in Germany, he combines pragmatic engineering leadership with deep algorithmic expertise and a track record of moving RL from prototypes into production.
10 years of coding experience
27 years of employment as a software developer
B.S., Biochemistry, B.S., Biochemistry at Ruhr University BochumDoctor of Philosophy - PhD, Biomathematics, Bioinformatics, and Computational Biology, Doctor of Philosophy - PhD, Biomathematics, Bioinformatics, and Computational Biology at Universität Witten/HerdeckeBiomathematics, Bioinformatics, and Computational Biology, Biomathematics, Bioinformatics, and Computational Biology at Columbia University
English, German, Spanish
Stackoverflow
81reputation
2kreached
3answers
1question
Github Skills (19)
unreal-engine-510
unreal-engine-410
python10
reinforcement-learning10
tensorflow10
unreal10
deep-reinforcement-learning10
documentation10
machine-learning9
game-development9
deep-learning8
controlling8
pytorch8
libpng6
ray6
Programming languages (4)
Github contributions (5)
ray-project/ray
Jan 2020 - Jan 2023
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Role in this project:
Backend Developer
Backend DeveloperContributions:5199 reviews, 843 commits, 2847 PRs in 3 years 1 month
Contributions summary:Sven's commits focus on documentation and fixes within the RLlib library, specifically the DreamerV3 algorithm related to RLlib. The user's work primarily involves making changes to documentation files and training-related fixes. This includes fixing issues related to the `rllib train` command, handling floating-point errors, and providing a utility for policy-only cases, with the implementation involving code modifications in different python files.
pythonconsistsruntimetensorflowserving
tensorforce/tensorforce
Dec 2017 - Mar 2018
Tensorforce: a TensorFlow library for applied reinforcement learning
Role in this project:Backend Developer
Backend DeveloperContributions:26 commits, 17 PRs, 29 comments in 3 months
Contributions summary:Sven primarily worked on extending the functionality of the Unreal Engine environment within the Tensorforce library. They implemented an adapter for UE4, adding the `seed` method to the `Environment` class and integrating it into the `contrib` folder. Further work involved completing the UE4 environment adapter and test script. Their contributions show a focus on connecting Tensorforce with UE4 for reinforcement learning tasks.
tensorflow-librarytensorforcereinforcement-learningdeep-reinforcement-learningmachine-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.