Autonomy Engineer Intern - Reinforcement Learning (2027, Zurich)

About the role

Skydio builds autonomous drones used in inspection, public safety, defense, cinematography and more. This 2027 internship in Zurich focuses on developing and deploying reinforcement learning and adjacent policy-learning methods so that aircraft plan, navigate and control themselves more intelligently, safely and reliably across handheld apps, ground control, cloud autonomy services and fleet workflows.

Key responsibilities

• Train policies that adapt online to cluttered 3D scenes such as forests, bridges and urban canyons, complementing the stack for obstacle avoidance and dynamic goal-seeking.
• Fuse learned cost shaping and value functions with trajectory optimization for smooth, agile flight within tight safety envelopes and mission constraints.
• Build scalable datasets and training loops with Isaac Lab, domain randomization, residual learning and safety filters, validated on real drones weekly.
• Learn assistive policies that blend pilot intent, autonomy priors and uncertainty-aware behaviors for intuitive control handoffs.
• Explore decentralized coordination for coverage, pursuit and collaborative mapping with minimal communications.

Required profile

• PhD student in Robotics, Machine Learning, Controls or a related field.
• Strong fundamentals in RL, control theory and motion planning, with comfort with safety and robustness concepts.
• Hands-on experience with robotics simulation and sim-to-real techniques.
• Experience training or deploying policies for navigation, manipulation or locomotion on real robots or autonomous vehicles.
• Nice to have: publications (CoRL, ICRA, IROS, RSS, NeurIPS), onboard inference optimization (TensorRT, quantization, sparsity), and familiarity with diffusion policies, IL/BC, offline RL and model-based RL.

Required skills

• Proficiency in Python (PyTorch, JAX, Ray RLlib).
• At least one of C++ or CUDA.
• Robotics simulation tools such as Isaac Lab, MuJoCo or PyBullet.

What we offer

• Hourly compensation of $47 for undergraduates, $53 for masters and $70 for PhD students, varying with skill level and experience.
• Full-time employees are eligible for benefit plans and incentives and stipends.
• Prototype in simulation, then flight test on production aircraft and edge compute, with cross-disciplinary mentorship from perception, mapping, controls and product teams.