Grzegorz Bartyzel is a Staff Data Scientist specializing in Physical AI with 11 years of experience building real-world robotic systems that bridge deep learning, reinforcement learning, and control. He leads VLA robotics at Grid Dynamics, integrating foundation models and production inference (NVIDIA Triton) into robot platforms, and previously drove off-road trajectory planning and patent-backed innovations at Stellantis. His work spans end-to-end pipelines—from ROS 2 control abstractions and RL-based insertion systems with >95% success to LIDAR perception and novel benchmarking metrics that revealed systemic bottlenecks. A PhD-trained engineer who dresses research rigor in production-ready architecture, he mentors teams on multimodal models and ML workflows while organizing a local robotics community in Poland. Humorous but grounded, his GitHub motto “Robots also can learn to do stupid things” reflects a pragmatic approach to failure-driven learning in complex physical systems.
11 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at AGH University of Krakow
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
Grzegorz Bartyzel - Staff Data Scientist - Physical AI