Reinforcement Learning Engineer

The role

Reinforcement Learning experts will develop and deploy RL algorithms to enhance robot capabilities. This includes designing algorithms, optimizing training pipelines, and collaborating with robotics engineers.

What you will do

• Design and implement reinforcement learning algorithms for various robotics tasks
• Develop and optimize RL training pipelines in both simulation and real-world environments
• Collaborate with robotics engineers to integrate RL models into production systems
• Conduct experiments to evaluate and improve algorithm performance
• Scale training infrastructure for efficient learning across multiple robots

Required qualifications

• Strong experience with reinforcement learning (PPO, SAC, TD3, DDPG, etc.)
• Hands-on experience with robotics systems (simulation or real robots)
• Proven track record applying RL to manipulation, locomotion, or navigation tasks
• Proficiency in Python and deep learning frameworks (PyTorch, TensorFlow, JAX)
• Strong understanding of robot kinematics, dynamics, and control
• Experience with GPU-based simulation such as Isaac Gym, Isaac Lab, SAPIEN, etc.

Nice to have

• Experience with distributed RL training systems
• Experience with sim-to-real transfer techniques
• Publications in robotics or RL conferences (CoRL, ICRA, RSS, NeurIPS, ICLR, ICML, etc.)

About the company

Dexmate is building the foundation for physical AI by combining a new generation of robots with a universal Physical AI OS. Their mission is to democratize robotics by delivering a plug-and-play platform for developers, researchers, and enterprises.