Founding Research Engineer, Robot Learning

About the Role

Join a robotics data infrastructure team as its first robot learning hire. You will train robot policies on synthetic data, rigorously measure its impact, and use the findings to guide data development and product requirements.

What You'll Do

• Train and fine-tune robot policies using methods such as VLA fine-tuning, imitation learning, diffusion policies, and reinforcement learning in simulation.

• Evaluate manipulation and grasping policies using public benchmarks and consistent experimental protocols.

• Run controlled comparisons with fixed seeds and checkpoints, varying training data to measure performance changes.

• Translate evaluation results into written data specifications, including requirements for fidelity and variation.

• Share findings through research publications and demos, and contribute to customer technical discussions.

• Help build and lead the robotics team as it grows.

What We're Looking For

• At least 6 years of hands-on robot learning experience, including work in industry and a university research lab.

• A graduate degree in robotics, machine learning, or a related field.

• Experience training and evaluating robot policies in simulation with Isaac Sim, Isaac Lab, MuJoCo, or equivalent tools.

• Practical experience with manipulation or grasping policies and methods such as OpenVLA, ACT, diffusion policy, behavior cloning, or reinforcement learning.

• Strong Python and PyTorch skills, with experience using evaluation results to guide data or simulation changes in subsequent training iterations.

Compensation & Benefits

Base salary is $260,000 to $300,000 USD annually. Visa sponsorship is not available.

Location

Hybrid role based in San Francisco, United States.