СШАRobotics Engineer - Teleoperation focus
1 мес. назад
СШАOnsite
teleoperationdata-collectionsoftware-toolinghardwaredata-processingdata-augmentation
Robotics Engineer responsible for teleoperation pipeline development, hardware and software integration, and data collection for machine learning model training.
О компании
- We're hiring Robotics Engineers to create a Data-Collection Engine that can power our model training and deployment. You will own both the software and hardware of our teleoperation pipeline, creating large quantities of high-quality data across multiple robot modalities (arms and mobile robots) to be used by our research and deployment teams. You will collaborate with our team of teleoperators to ensure that their experience is intuitive and ergonomic, thereby increasing data quality and throughput.
- General Robotics is building the intelligence grid for physical AI — the platform that makes any robot, from robotic arms to humanoids, genuinely intelligent. Headquartered in Redmond, Washington, we're venture backed, including by Accenture, who invested in General Robotics in 2026 to advance Physical AI-powered robotics in manufacturing and logistics, and we're also part of Microsoft's Startups Pegasus Program. Our team's work spans some of the most widely adopted robotics and AI research to come out of Microsoft Research, Google Research and DeepMind — including AirSim, PACT, ClimaX, Tensorflow Object Detection and VideoPoet.
Обязанности
- Rapidly design and fabricate electromechanical teleoperation devices to support research experiments and new data collection techniques.
- Design the software tooling needed to collect data for VLA training at scale, including both the interface for teleoperators and backend data-processing pipeline
- Define what “good data” means as concrete, measurable metrics and implement an automated pipeline that ensures data quality.
- Build data-augmentation and data adaptation pipelines to convert human video and video collected with less robot hardware into usable training data.
- Contribute to publications and open-source releases.
- Partner with customers to take manipulation capabilities from prototype to deployed product.
Требования
- Bachelor's degree in Robotics, Computer Science, Computer Engineering, Electrical Engineering, relevant technical field, or equivalent practical experience.
- Job or Research experience in machine learning, robotics, and computer vision.
- Production-ready Python. C++ and Rust are also a plus!
- Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment.
- MS or PhD in Robotics, Computer Science, Computer Engineering, Electrical Engineering, or a related technical field.
- Have strong fundamentals in rigid body kinematics, coordinate frame transforms, camera calibration, and robotic controls
- Demonstrated projects using robotic middleware platforms such as ROS2 or Zenoh, and comfort writing multithreaded, asynchronous code
- Hands-on experience with modern teleoperation methods for robot arms and mobile manipulators (including leader/follower setups, UMI, VR/AR, etc)
- Hands-on experience with modern manipulation policies — VLAs, world action models, reinforcement learning, imitation learning, diffusion or flow-matching policies, or agentic robot policies.
- Broad experience with many different industrial robots, and deep knowledge of modern sensing hardware: RGB and RGB-D cameras, LiDAR, force and tactile sensing.
- Judgment about systems constraints — latency, throughput, compute budget, memory — and the ability to factor them into model and architecture choices.
Другое
- This role is open to candidates currently based in and authorized to work in the US.