Machine Learning: Whole-Body Control

What you'll do

• Train whole-body policies and design rewards and curricula for stable long-horizon learning.
• Build scalable simulation environments and run large-scale GPU training experiments.
• Own sim-to-real transfer using domain randomization and structured evaluation.

What they ask for

• Very strong coding skills in Python, C++, or Rust.
• Strong foundations in modern reinforcement learning.
• Experience training embodied control policies and hands-on robotics simulation experience.
• Solid intuition for dynamics, contact, and actuation; comfortable running large-scale GPU experiments.

Nice to have

• CUDA

Pay

$200K – $350K (base salary)

Tools

Python, C++, Rust, CUDA, IsaacLab, MuJoCo

AI focus

Train reinforcement-learning control policies for robot locomotion, manipulation, and coordinated motion; transfer them from simulation to real-world deployment.