Kevin Fu
Senior Machine Learning Engineer at Tesla
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolKevin Fu is a machine learning engineer focused on safety-critical autonomy, currently developing end-to-end deep learning models for Tesla Autopilot in the San Francisco Bay Area. With seven years of experience spanning industry and academia, he wrote an MSCS thesis on deep reinforcement learning for heterogeneous multi-agent systems and co-led a CoRL 2025 paper on the topic. He has hands-on AV expertise from Zoox localization work and shipping perception/mapping improvements at Greenzie, plus practical robotics leadership guiding RoboJackets to its first international qualification in four years. Kevin blends research rigor with production pragmatism—adapting state-of-the-art vision and RL methods to real-world sensors like rolling-shutter cameras and safety-critical collision-avoidance systems.
7 years of coding experience
5 years of employment as a software developer
Master's degree Computer Science (Machine Learning), Master's degree Computer Science (Machine Learning) at Georgia Institute of TechnologyAdvanced Studies Diploma, Advanced Studies Diploma at Thomas Jefferson High School for Science and Technology
Github Skills (50)
robotics10
multi-agent-reinforcement-learning10
gtsam10
distributed-computing10
decision-making10
robocup10
structure-from-motion10
3d-reconstruction10
reinforcement-learning9
simulator9
simulation9
pytorch9
vectorization9
machine-learning9
ai9
Programming languages (10)
Github contributions (5)
kfu02/JaxMARL
Jun 2024 - Dec 2024
Multi-Agent Reinforcement Learning with JAX
Contributions:11 reviews, 42 PRs, 109 pushes in 5 months
jaxmulti-agent-reinforcement-learning
GT-STAR-Lab/VectorizedMultiAgentSimulator
Oct 2023 - Jun 2024
VMAS is a vectorized framework designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
Contributions:21 reviews, 27 PRs, 52 pushes in 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.