Fullstack engineer

We are an AI technology company focused on embodied intelligence and robotics. We are rapidly scaling the engineering deployment of robotic data collection and imitation learning systems. We are looking for a Full-stack Robotic Engineer who can bridge hardware, sensors, data pipelines, and algorithms, taking end-to-end ownership of deploying embodied AI capabilities on robotic platforms.

Responsibilities:

• Maintain and continuously improve the embodied AI data collection system, including multimodal sensor synchronization, data pipelines, storage, and downstream annotation tools.
• Independently implement end-to-end deployment of imitation learning, DAgger, teleoperation, and related algorithms on robotic systems, covering data collection, model training, inference deployment, and on-site optimization.
• Develop and improve data quality assurance processes, including timestamp synchronization, coordinate system alignment, anomaly detection, and rapid troubleshooting of failed data collection.
• Define and maintain robot software interfaces and communication protocols (e.g., ROS2, DDS) to support fast replication of data collection and deployment systems across multiple sites.
• Support on-site data collection and algorithm deployment, produce technical documentation, and continuously improve data 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 programming skills in Python and C++, with experience in Linux system development and debugging.
• Familiar with ROS/ROS2, including Topics, Services, Actions, parameter management, and Launch systems (preferable)
• Familiar with robotic arm control interfaces (e.g., Universal Robots, Franka, xArm, or proprietary robotic arms), including drivers, kinematics, and high-level APIs.
• Experience with common robotics hardware interfaces such as CAN, EtherCAT, RS485, and USB, as well as sensor integration (IMUs, depth cameras, force/torque sensors, etc.).
• Hands-on experience training and deploying deep learning models using PyTorch, with the ability to independently manage the full workflow from data preparation to deployment.
• Comfortable using AI-assisted development tools (e.g., Claude Code, Cursor) to improve engineering productivity.

Preferred Qualifications:

• End-to-end project experience in embodied AI, imitation learning data collection, and algorithm deployment.
• Familiarity with imitation learning frameworks such as Diffusion Policy, ACT, and VLA, including training and deployment workflows.
• Experience with robotics data formats such as SVO2, ROS bag, HDF5, and LeRobot Dataset.
• Experience integrating motion capture systems and devices such as VIVE Tracker, OptiTrack, or motion capture gloves.
• Experience with video encoding and decoding technologies (e.g., H.264, H.265, NVIDIA Jetson hardware acceleration).
• Strong English reading and writing skills, with the ability to read research papers and open-source documentation.