Autonomy Engineer Intern, Reinforcement Learning, 2027 (Zurich)

The role

Develop and deploy reinforcement learning and policy-learning methods to make Skydio aircraft plan, navigate, and control themselves. Work involves training policies for navigation, planning, sim to real, human-in-the-loop control, and multi-agent coordination.

What you will do

• Train policies that adapt online to cluttered 3D scenes
• Fuse learned cost shaping or value functions with trajectory optimization
• Build scalable datasets and training loops with Isaac Lab, domain randomization, residual learning, and safety filters
• Validate on real drones weekly
• Learn assistive policies that blend pilot intent, autonomy priors, and uncertainty-aware behaviors
• Explore decentralized coordination for coverage, pursuit, and collaborative mapping

Required qualifications

• PhD student in Robotics, Machine Learning, Controls, or related field
• Strong fundamentals in RL, control theory, and motion planning
• Comfort with safety/robustness concepts
• Proficient in Python (PyTorch/JAX/Ray RLlib)
• At least one of C++ or CUDA
• Hands-on experience with robotics simulation (Isaac Lab/MuJoCo/PyBullet)
• Experience with sim2real techniques
• Experience training/deploying policies for navigation, manipulation, or locomotion on real robots or autonomous vehicles

Nice to have

• Publications (CoRL, ICRA, IROS, RSS, NeurIPS)
• Experience with onboard inference optimization (TensorRT, quantization, sparsity)
• Familiarity with modern policy learning beyond vanilla RL: diffusion policies, IL/BC, offline RL, model-based RL
• Experience with multi-agent RL or distributed training

About the company

Skydio is the leading US drone company and the world leader in autonomous flight. The team combines expertise in artificial intelligence, hardware and software product development, operational excellence, and customer obsession.