Member of Technical Staff

Responsibilities

• Maintain and iterate on embodied AI data collection systems, including multimodal sensor synchronization, data pipelines, storage, and annotation toolchains.
• Integrate, calibrate, and routinely maintain ZED, RealSense, and industrial camera systems and robotic arms.
• Deploy imitation learning, DAgger, and teleoperation algorithms end to end on robots, including data collection, model training, inference deployment, and on-site tuning.
• Develop data quality assurance mechanisms for timestamp synchronization, coordinate frame alignment, anomaly detection, and collection-failure diagnosis and repair.
• Define and maintain robot-side software interfaces and communication protocols using ROS2 and DDS.
• Support on-site data collection and algorithm deployment, document technical processes, and improve collection efficiency and model performance.

Requirements

• Bachelor's degree or above in Robotics, Automation, Computer Science, or a related field, with 3+ years of relevant experience.
• Strong Python and C++ programming skills and familiarity with system-level development and debugging in Linux environments.
• Expertise in ROS and ROS2, including Topics, Services, Actions, parameter management, and the Launch system.
• Experience integrating and calibrating camera systems, including intrinsics, extrinsics, multi-camera synchronization, and ZED, RealSense, or similar RGB-D and stereo cameras.
• Experience with robotic arm control interfaces such as UR, Franka, xArm, or in-house arms, including driver layers, kinematics, and high-level APIs.
• Familiarity with CAN, EtherCAT, RS485, USB, IMUs, depth cameras, and force/torque sensors.
• Experience training and deploying deep learning models, with proficiency in PyTorch and the full workflow from data preparation and training through inference and deployment.
• Proficiency using AI coding tools such as Claude Code and Cursor in daily development.
• Preferred experience with embodied AI or imitation-learning data collection and deployment, Diffusion Policy, ACT, VLA, SVO2, ROS bag, HDF5, LeRobot datasets, camera hardware triggering, PTP synchronization, VIVE Trackers, OptiTrack, motion-capture gloves, video codecs, and Jetson hardware codecs.
• Fluent written English and ability to read research papers and open-source project documentation.

Benefits

• Competitive compensation package.
• Flat, open engineering culture with involvement in technical decisions.
• Well-equipped hardware lab resources for rapid prototyping and iteration.
• Flexible work arrangements and ongoing learning and internal tech-sharing programs.
• End-to-end ownership and autonomy across data collection, algorithms, and deployment.