Robotics Engineer - Humanoids focus

The role

This person will conduct research and deploy whole body humanoid models. They will train RL/IL policies for loco-manipulation tasks and design high fidelity simulation environments.

What you will do

• Train and deploy RL/IL policies for loco-manipulation tasks
• Design high fidelity simulation environments to advance sim-to-real transfer
• Define research goals informed by practical engineering concerns
• Contribute to experiments including designing details, writing code, and running evaluations
• Contribute to publications and open-sourcing efforts
• Partner with the robot deployment team to ship RL trained policies to production customer sites

Required qualifications

• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• Research experience in machine learning, robotics, and computer vision
• Experience with developing robotics algorithms or machine learning models at scale
• Programming experience in Python/C++
• Good understanding of deep learning frameworks like Pytorch or Jax
• Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment

Nice to have

• Master's/PhD in Robotics, Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• Direct experience in robotics, computer vision, or machine learning research
• First author publications at peer-reviewed AI and robotics conferences (e.g., NeurIPS, CVPR, ICML, ICLR, ICRA, IROS, CORL)
• Experience with high fidelity simulation platforms such as Isaac Lab, Mjlab, ManiSkill, MolmoSpaces etc.
• Experience working with training and deploying policies for whole-body humanoid tasks - reinforcement learning, imitation learning, and classical approaches
• Experience working with modern computer vision algorithms and sensors (RGB, RGB-D cameras, LIDAR.), 3D (meshes, point clouds, etc.), segmentation, tracking, detection
• Experience with domain randomization, reward shaping, and the engineering needed to bridge sim-to-real gap for humanoid policies
• Experience working with real-world deployment of proprioceptive and visual humanoid policies
• Good understanding of systems considerations and the ability to factor these into model choices

Before you apply

• Role is open to candidates currently based in and authorized to work in the US
• Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment

About the company

General Robotics is building the intelligence grid for physical AI. Headquartered in Redmond, Washington, the company is venture backed and part of Microsoft's Startups Pegasus Program.