Robotics Software Engineer, Learned Manipulation Policies and Post-Training
Humanoid robotics company in the Bay Area building AI-powered robots for industries like manufacturing and logistics
| Employer | Humanoid robotics company in the Bay Area building AI-powered robots for industries like manufacturing and logistics (not named) |
|---|---|
| Location | Sunnyvale, CA (Bay Area) · On-site |
| Type & level | Full-time · Mid-level |
| Pay | USD 180k–240k base Source: pay range stated in the source posting |
| Visa path | O-1A fit |
| Role family | Robot Manipulation & Dexterous Control Researcher |
About the role
This engineer owns the path from demonstration data to deployed manipulation policies on physical humanoid hardware. The focus is post-training methods that adapt and improve policies on real tasks. The role works closely with simulation, data, hardware and systems teams to make those policies reliable across a fleet.
What you'll do
- Implement and deploy learning-based manipulation policies that perform reliably on real hardware.
- Adapt policies to new tasks and hardware using RL fine-tuning, distillation and interactive imitation learning.
- Build data pipelines for teleoperation and demonstration collection, retargeting, aggregation and curation.
- Develop visuomotor policies for grasping, in-hand and whole-arm manipulation with low-latency execution.
- Define evaluation metrics and regression tests in simulation and on the robot to guide decisions.
- Work with simulation, data, hardware and systems teams to diagnose system-level issues.
Requirements
- MS with 3+ years of relevant experience, or a recent PhD, in robotics, computer science, electrical engineering or a related field.
- Strong robotic manipulation experience, including grasping, in-hand or whole-arm control, with hardware deployment.
- Hands-on training and debugging of learned policies, including RL fine-tuning, distillation and DAgger-style imitation learning.
- Proficiency in Python, C++ and PyTorch or JAX, with real-time robotic software experience.
- Experience with demonstration and teleoperation data and building policy evaluation pipelines.
Nice to have
- Experience with physics simulators for policy training and validation.
- Experience adapting large general-purpose manipulation policies to specific tasks and embodiments.
- Experience with VR or haptic teleoperation interfaces and retargeting.
- Experience integrating tactile feedback into manipulation pipelines.
- Familiarity with 6D pose estimation, point cloud processing or visual servoing.
Pay & benefits
USD 180k–240k base. The posting does not list benefits.
Pay source: pay range stated in the source posting. Market data, not an offer from O1DMatch.
Visa path
People in learned-manipulation roles often build O-1A evidence from publications, patents, open-source contributions, citations, and documented impact on deployed robotic systems. The posting states no citizenship restriction. An employer like this or a U.S. agent can file an O-1A petition, and approval depends on the individual's evidence.
How to get matched
- Take the free eligibility checkAn AI review of your background against the eight O-1 criteria, at check.o1dmatch.com.
- Create your profile with code WORKWITHUSIt unlocks the Starter plan at no cost. Tell us your field and the work you do today.
- Upload your evidenceEach document is sorted under the criterion it supports, and your criteria map shows what is still missing.
- Get matchedWe match strong profiles with U.S. employers hiring for roles like this one. Gigs you confirm with verified companies count toward your itinerary, and at a score of 75 we connect you with an immigration attorney.
This listing describes a real U.S. posting so you can see what employers ask for. O1DMatch does not represent that employer and does not hold this opening; applying matches you with employers hiring for this kind of role. No visa outcome is promised.