AI Software Engineer, Reinforcement Learning (f/m/d)

• Develop reinforcement learning algorithms for dexterous manipulation and robotic hands

• Design training environments, reward functions and learning curricula for complex manipulation tasks

• Train and evaluate policies in simulation and on real robotic hardware

• Develop methods for efficient exploration, learning and policy optimisation

• Work on sim-to-real transfer and robustness of learned policies

• Build software infrastructure for large-scale training, evaluation and experimentation

• Analyse policy behaviour and failure modes and use these insights to improve training

• Integrate learned policies with robotics and control systems

• Work closely with simulation, controls and robotics engineers to bring learned behaviours onto the real hand

• Contribute to scalable approaches for learning new manipulation skills

• Degree in Computer Science, Robotics, AI, Electrical Engineering or a related field

• Strong software engineering skills in Python and preferably C++

• Hands-on experience with reinforcement learning and deep learning

• Strong understanding of RL concepts such as policy optimisation, value functions, exploration and reward design

• Experience with PyTorch or a similar deep learning framework

• Experience working with robotic systems and simulation environments

• Good understanding of robot kinematics, dynamics and control

• Strong analytical and problem-solving skills

• A hands-on mindset and enthusiasm for testing learning algorithms on real robotic systems

• Experience with dexterous manipulation, grasping or robotic hands

• Experience with sim-to-real reinforcement learning

• Experience with PPO, SAC or other modern RL algorithms

• Experience with Isaac Lab, Isaac Sim, MuJoCo or similar environments

• Experience with distributed or large-scale RL training

The next chapter of robotics won't be built in a lab. It will be built by people who care about what happens when technology meets the real world. At TACTILIA, you'll work on one of the hardest open problems in robotics: giving machines the dexterity, reliability and robustness to interact with the physical world at industrial scale. The technology is taking shape, the team is being built, and the standards around robotic hands and their skills are still open. That means your decisions will have a lasting impact - not just on a product, but on what comes next for Physical AI.