Lead Robot Learning & Embodied AI Architect

Origin; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Job summary

Origin is building Physical AI for the built world, deploying autonomous robots on construction sites. You will own the lifecycle of learned components from data collection and model training to edge deployment on Jetson platforms, ensuring production safety and real-world performance.

The role focuses on defining the Robot Learning roadmap, building learned policies for manipulation tasks, and advancing sim-to-real strategies with NVIDIA Isaac Sim and ROS2 integration.

Qualifications

• Strong Python and PyTorch; capable of modifying research codebases and open-source VLA implementations.
• Experience in at least two of: imitation learning, RL, VLA/VLMs, robot learning from demonstration, sim-to-real.
• Track record deploying ML on real robots and debugging why they fail on actual hardware.

Responsibilities

• Define the technical roadmap for Robot Learning and Embodied AI.
• Build and deploy learned policies for real-world mobile manipulation and contact-rich tasks.
• Develop imitation learning, reinforcement learning, VLA, and learning-from-demonstration systems.

Skills

Python

PyTorch

ROS2

Imitation Learning

Reinforcement Learning

Open-source ML

Education

BS/MS/PhD in CS/Robotics/ML

Tools

NVIDIA Isaac Sim

TensorRT

ONNX

CUDA

Job description

Origin is building Physical AI for the built world, deploying autonomous robots on construction sites. You will own the lifecycle of learned components from data collection and model training to edge deployment on Jetson platforms, ensuring production safety and real-world performance.

The role focuses on defining the Robot Learning roadmap, building learned policies for manipulation tasks, and advancing sim-to-real strategies with NVIDIA Isaac Sim and ROS2 integration.