Applied Scientist, Safe RL, Robotics, SAF Lab
Core
Lead the development of safe reinforcement learning (RL) algorithms for legged locomotion, enabling dynamic robots to walk, run, and recover from disturbances on physical hardware.
Role type
Applied Scientist, Safe RL, Robotics
Builds
Safe RL policies for legged robots, sim-to-real transfer pipelines, and large-scale training infrastructure
Domain
Robotics, Reinforcement Learning, Safety-Critical Control
Deliverable
production ML models
Required skills
Reinforcement learning, sim-to-real transfer, legged robot dynamics, whole-body control, Python, deep learning frameworks (PyTorch, JAX), physics simulators (Isaac Gym/Sim, MuJoCo, PyBullet)
Preferred skills
Safety-critical control (CBF, safety filters), model-based control (MPC, QP), stability theory, hierarchical RL, real-time deployment constraints
Technologies
PyTorch, JAX, Isaac Gym/Sim, MuJoCo, PyBullet
Responsibilities
Design and deploy RL policies for dynamic legged locomotion; develop sim-to-real transfer pipelines; integrate control-based methods with RL; maintain large-scale training infrastructure; evaluate policy performance via simulation and hardware experiments; publish research at top-tier venues
Seniority
Senior, hands-on IC
