Robot Learning Intern
About the role
You'll work alongside our Robot Learning Engineer, collecting force-rich robot data and showing what it's worth. You'll run real collection sessions, build pieces of the pipeline, and train policies on data you helped gather.
What you'll do
- Run data collection sessions on our teleoperation system: setup, calibration, operator coordination and quality checks
- Build and improve the data pipeline: synchronization, labeling, export and visualization
- Train and evaluate baseline policies on collected data, and run ablations
- Help design and run studies, and analyze the results
- Document protocols so collection is repeatable
What we're looking for
- Pursuing a BS, MS or PhD in robotics, computer science, machine learning, mechanical engineering or a related field
- Python, PyTorch and Linux
- Hands-on experience with real robots, from a research lab, student team or personal projects
- Care with data. You notice when something is off.
Nice to have
- An imitation learning or RL project on real hardware
- ROS/ROS2, LeRobot or RLDS
- A published or submitted paper
About Mundane
Mundane builds force-feedback teleoperation for dangerous, hands-on work. A skilled tradesperson wears our exoskeleton and works through a robot on site, seeing in stereo and feeling the forces it meets, from outside the hazard. We're starting with energized electrical work and expanding across the trades. Every job also produces the force-rich data that robot learning is missing. We're a small, venture-backed team in Palo Alto.
Work authorization
Please tell us whether you're authorized to work in the US and whether you'll need visa sponsorship now or in the future.
Equal opportunity
Mundane is an equal opportunity employer. We welcome applicants from every background and don't discriminate on the basis of any legally protected characteristic.