Robotics Engineer – Locomotion

UMA; Paris; Sur place; EUR 70 000 - 90 000; Plein temps

Avantages offerts par ce poste

Inclusive workplace

Résumé du poste

UMA, a Paris-based robotics startup, is hiring a robotics engineer to train and deploy RL locomotion policies on our humanoid robots. You will build the stack to train in simulation and deploy on hardware, bridging sim2real with system identification and domain randomization.

You will work with Python and C++, developing the control stack, and collaborating across teams to push the humanoid platform beyond existing units.

Qualifications

• Strong background in controls, rigid-body dynamics, and robot learning.
• Fluency in Python and C++.
• Experience with simulation tools (MJLab, Isaac Lab, Isaac Gym).
• Bonus: experience on humanoid platforms beyond the Unitree G1.

Responsabilités

• Train locomotion policies in simulation that transfer to hardware.
• Develop the stack that deploys learned policies.
• Bridge the sim2real gap with techniques such as system identification and domain randomization.
• Build motion retargeting pipelines that turn human demonstration data into reference trajectories for RL.
• Build tele-op systems for data collection

Connaissances

Python

C++

Robot learning

Controls

Rigid-body dynamics

Outils

MJLab

Isaac Lab

Isaac Gym

Description du poste

Your Mission

UMA builds general-purpose humanoid robots. Founded in Paris in 2025 by alumni of Tesla Optimus, Google DeepMind, and LeRobot, we're building the humanoid and its control stack from the ground up.

Your Mission

UMA builds general-purpose humanoid robots. Founded in Paris in 2025 by alumni of Tesla Optimus, Google DeepMind, and LeRobot, we're building the humanoid and its control stack from the ground up.

We're hiring a robotics engineer to train and deploy RL locomotion policies on our humanoids.

Responsibilities

• Train locomotion policies in simulation that transfer to hardware
• Develop the stack that deploys learned policies
• Bridge the sim2real gap with techniques such as system identification and domain randomization
• Build motion retargeting pipelines that turn human demonstration data into reference trajectories for RL
• Build tele-op systems for data collection

Requirements

• Strong background in controls, rigid-body dynamics, and robot learning
• Experience with mjlab, Isaac Lab, or Isaac Gym
• Fluency in Python and C++
• Bonus: experience on humanoid platforms beyond the Unitree G1

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.