Reinforcement Learning Engineer – Robotics & Drone Systems

About the role

The Technology Innovation Institute is seeking a Reinforcement Learning Engineer to join its Robotics Research Center. You will develop and deploy advanced RL solutions for robotics, UAV swarms, and autonomous agents, turning cutting‑edge research into real‑world prototypes.

Key responsibilities

• Design, implement, and optimise RL algorithms for robotic platforms and drone systems.
• Develop multi‑agent reinforcement learning frameworks for coordination and cooperative decision‑making in UAV swarms.
• Build efficient training pipelines for large‑scale simulations and ensure smooth simulation‑to‑real transfer.
• Stay current with state‑of‑the‑art RL methods and investigate hybrid learning paradigms.
• Integrate RL solutions with robotics middleware such as ROS2 and maintain reproducible Docker‑based environments.

Required profile

• Strong theoretical foundation in reinforcement learning, including policy‑gradient, Q‑learning, actor‑critic and hierarchical methods.
• Hands‑on experience with multi‑agent and federated learning approaches.
• Proven ability to bridge research and deployment in real‑world robotic or aerial platforms.

Required skills

• Python programming
• C++ programming
• RL frameworks: Ray RLlib, Stable Baselines3
• Simulation tools: PyBullet, Isaac Gym, Gazebo, MuJoCo, AirSim
• AI libraries: PyTorch, TensorFlow, JAX
• Docker and distributed computing
• Robotics middleware: ROS2