RL Locomotion Engineer for Legged Robots

Logoslabs; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Field AI is seeking a Robotics Autonomy Engineer – Locomotion to design and deploy state-of-the-art RL-based locomotion controllers for legged and humanoid robots. You will architect scalable RL pipelines, integrate Isaac Gym/Lib, and optimize sim-to-real transfer.

You will collaborate with perception, planning, and hardware teams, refine models with real-world telemetry, and drive deployment from experiments to field testing. Strong background in RL for continuous control is essential.

Qualifications

• Master's degree or higher in Robotics, Computer Science, Engineering, or related field (PhD a strong plus).
• Deep expertise in reinforcement learning, especially for continuous control tasks.
• 2+ years of experience developing and deploying locomotion policies for robotic systems.
• Proficiency with simulation tools such as Isaac Gym, Isaac Lab, MuJoCo, or PyBullet.
• Strong understanding of contact dynamics, control theory, and kinematics.
• Experience with legged and/or humanoid robots (quadrupeds, bipedal systems, or exoskeletons).
• Solid Python and/or C++ development skills in Linux-based environments.
• Familiarity with machine learning frameworks (PyTorch, TensorFlow).

Responsibilities

• Design RL-based locomotion control pipelines.
• Develop and test locomotion behaviors for legged/humanoid robots.
• Own simulation and evaluation environments using Isaac Sim and related tools.
• Collaborate across perception, planning, and hardware teams to close learning-to-execution loop.
• Lead deployment workflows from experiment to field robot testing.

Skills

RL for locomotion

Continuous control

Python/C++

Linux environment

PyTorch / TensorFlow

Education

Master's degree or higher in Robotics/CS/Engineering

Tools

Isaac Gym

Isaac Lab

MuJoCo

PyBullet

Job description

Field AI is seeking a Robotics Autonomy Engineer – Locomotion to design and deploy state-of-the-art RL-based locomotion controllers for legged and humanoid robots. You will architect scalable RL pipelines, integrate Isaac Gym/Lib, and optimize sim-to-real transfer.

You will collaborate with perception, planning, and hardware teams, refine models with real-world telemetry, and drive deployment from experiments to field testing. Strong background in RL for continuous control is essential.