Your Mission
Develop and refine simulation environments that capture the physics and nuance of humanoid locomotion
Write firmware, middleware, develop system identification, tele-op systems and whole body control strategies
Create control pipelines that go beyond stability—designing walks that feel natural, expressive, and adaptable
Prototype controllers in simulation, stress-test them across varied terrains and scenarios, then bring them onto real hardware
Push the limits of reinforcement learning, optimization, and motion synthesis to achieve smooth, human-like gait patterns
Tune models and parameters to close the sim-to-real gap and make humanoid robots move with confidence
Work hand-in-hand with a fast-moving team building the next generation of general-purpose humanoids
What You Bring to the Table
Strong background in control, dynamics, or machine learning for robotics
Experience building or extending physics simulation environments (Mujoco, Isaac, Bullet, or custom engines)
Fluency in Python or C++ with an eye for clean, efficient code
Creativity and intuition for motion—balancing stability with style in robotic locomotion
Drive to own projects end-to-end: from prototyping ideas to seeing robots walk in the lab
Bonus: hands-on experience with humanoid robots, reinforcement learning for locomotion, or biomechanics / animation techniques
UMA is an inclusive workplace that values exceptional builders over perfect pedigrees. Whatever your background, identity, or journey, if you don't meet every criterion but believe you can have an outsized impact here, we strongly encourage you to apply
- Locations
- Paris, Paris, France