Autonomy Engineer Intern, Reinforcement Learning, 2027 (HQ)
About The Position
Skydio is seeking an Autonomy Engineer Intern to develop and deploy reinforcement learning and related policy-learning methods for autonomous drones. The role focuses on enabling aircraft to plan, navigate, and control themselves more intelligently, safely, reliably, and efficiently across Skydio’s ecosystem, including handheld apps, ground control, cloud autonomy services, and fleet workflows. The intern’s research is intended to be deployed on real missions in complex environments. The intern will train adaptive navigation and obstacle-avoidance policies for cluttered 3D environments; combine learned cost shaping or value functions with trajectory optimization; and build scalable simulation-to-reality datasets and training loops using techniques such as domain randomization, residual learning, and safety filters. The role also explores human-in-the-loop shared control and decentralized multi-agent coordination. Work includes prototyping in simulation and flight-testing on production-ready aircraft and edge compute, with weekly real-drone validation. The team emphasizes safety through formal constraints, uncertainty estimation, and conservative action filters, and offers cross-disciplinary collaboration with perception, mapping, controls, and product teams.
Requirements
- Be a PhD student in Robotics, Machine Learning, Controls, or a related field.
- Strong fundamentals in reinforcement learning, control theory, and motion planning.
- Comfort with safety and robustness concepts.
- Proficiency in Python and PyTorch, JAX, or Ray RLlib.
- Proficiency in at least one of C++ or CUDA.
- Hands-on experience with robotics simulation, such as Isaac Lab, MuJoCo, or PyBullet, and simulation-to-reality techniques.
- Experience training or deploying policies for navigation, manipulation, or locomotion on real robots or autonomous vehicles.
Nice To Haves
- Publications at venues such as CoRL, ICRA, IROS, RSS, or NeurIPS.
- Experience with onboard inference optimization, including TensorRT, quantization, or sparsity.
- Familiarity with policy-learning methods beyond vanilla reinforcement learning, including diffusion policies, imitation learning or behavioral cloning, offline reinforcement learning, and model-based reinforcement learning.
- Experience with multi-agent reinforcement learning or distributed training.
Responsibilities
- Train policies that adapt online to cluttered 3D scenes, complementing obstacle avoidance and dynamic goal-seeking capabilities.
- Combine learned cost shaping or value functions with trajectory optimization for smooth, agile flight within safety envelopes and mission constraints.
- Build scalable datasets and training loops using simulation-to-reality methods, including Isaac Lab, domain randomization, residual learning, and safety filters.
- Validate policies on real drones regularly.
- Develop assistive policies that blend pilot intent, autonomy priors, and uncertainty-aware behaviors for intuitive control handoffs.
- Explore decentralized multi-agent coordination for coverage, pursuit, and collaborative mapping with minimal communications.
- Prototype in simulation and flight-test on production-ready aircraft and edge compute.
- Collaborate with perception, mapping, controls, and product teams to move research toward field operations.
Benefits
- Skydio full-time employees are eligible to enroll in benefit plans and take advantage of a variety of incentives and stipends.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Career Level
Intern
Education Level
Ph.D. or professional degree
