Mantas Puida
Software Developer at KAYAK
Kaunas, Kaunas County, Lithuania
Summary
🤩
Rockstar🎓
Top SchoolMantas Puida is a software developer based in Kaunas with over 4 years of hands-on experience building responsive, high-performance React user interfaces and growing backend skills in Go. He has delivered production web apps with a strong focus on accessibility, mobile-first design, reusable components, and automated testing (Cypress), and recently contributed real-time features like activity feeds and messaging. At Krafit and Better Day™ Health he translated Figma designs into polished UIs while collaborating across design and QA, and now continues his career at KAYAK. Beyond web apps, he has notable open-source contributions to Unity-Technologies/ml-agents, integrating the Barracuda inference engine and optimizing model handling and compute shaders for better performance across Unity platforms. This combination of front-end craft, backend pragmatism, and ML-tooling experience positions him as a versatile engineer evolving toward full-stack and ML-infused projects. He thrives in fast-paced teams where design, performance, and maintainability meet.
15 years of coding experience
4 years of employment as a software developer
Bachelor's degree, Software Systems, Bachelor's degree, Software Systems at Kaunas University of Technology
Github Skills (10)
deep-reinforcement-learning10
machine-learning10
tensorflow10
unity3d10
csharp9
dotnet-core9
artificial-neural-networks9
neural-network9
python8
compute-shader8
Programming languages (5)
Github contributions (5)
Unity-Technologies/ml-agents
Feb 2019 - Nov 2019
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Role in this project:
ML Engineer
ML EngineerContributions:15 commits, 15 PRs, 35 pushes in 9 months
Contributions summary:Mantas significantly contributed to the integration of the Barracuda inference engine within the ML-Agents toolkit. Their work involved converting TensorFlow models to Barracuda-compatible formats, integrating the engine, and ensuring compatibility with various Unity platforms and examples. They also addressed issues related to model handling, action spaces, and memory management within the Barracuda implementation, improving performance and usability. Furthermore, the user made adjustments to the core compute shaders for activations and other core functionalities.
servedeep-reinforcement-learningtrainingunityreinforcement
mantasp/barracuda-burst-release
May 2019 - Jan 2020
Contributions:11 commits, 1 push, 11 branches in 8 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.