Founding Robot Learning Engineer — Policy Training & Eval

One Robot; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

One Robot in San Francisco builds world models and an evaluation platform for robot manipulation policies. You will train manipulation policies—VLAs, diffusion policies, and end-to-end imitation—on real robots and push the world model forward.

Join a small, ownership-driven team with fast iteration and direct responsibility, where validation on real hardware and deployment pressure drive progress.

Qualifications

• Strong Python and PyTorch coding skills.
• Experience training manipulation policies on real robots.
• Hands-on experience curating real-robot demonstration datasets.

Responsibilities

• Train manipulation policies: VLAs, diffusion policies, or end-to-end imitation models and run them on real robots.
• Validate the world model end-to-end: Train policies in simulation, deploy on real hardware, and find what doesn't transfer.
• Push policy capabilities forward: Build the infrastructure that lets policies train and improve on our platform.

Skills

Python

PyTorch

Real-robot policy training

Demonstration data

Job description

One Robot in San Francisco builds world models and an evaluation platform for robot manipulation policies. You will train manipulation policies—VLAs, diffusion policies, and end-to-end imitation—on real robots and push the world model forward.

Join a small, ownership-driven team with fast iteration and direct responsibility, where validation on real hardware and deployment pressure drive progress.