Reinforcement Learning Algorithms Engineer

Shifters is looking for a Reinforcement Learning Algorithms Engineer to develop and deploy advanced whole-body control policies for our autonomous quadruped robots. You will train robust behaviors for dynamic locomotion, balance, recovery, manipulation, and coordinated loco-manipulation tasks using large-scale physics simulation. The role includes reward and curriculum design, motion imitation, sim-to-real transfer, and close collaboration with robotics, mechatronics, and embedded teams to validate policies on real hardware.

Strong Python programming skills.

Practical experience with reinforcement learning, including policy-gradient methods such as PPO.

Experience developing, training, and evaluating algorithms in simulation.

Strong problem-solving skills and the ability to work independently and as part of a multidisciplinary team.

Experience with computer vision, ROS 2, robotics, or embedded computing platforms is an advantage.

Experience deploying algorithms on physical robotic systems is a strong advantage.