SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
xDOF is building the foundational infrastructure for embodied AI—data collection systems, exabyte-scale data warehouses, and software toolchains that enable frontier robotics labs to train general-purpose robots. The bottleneck in the field is high-quality training data, and xDOF is solving that at scale.
You will be a full-stack engineer owning the end-to-end implementation of embodied AI capabilities on robots. This is a high-autonomy role where you independently drive the entire pipeline from hardware integration through algorithm deployment.
Key Responsibilities:
- Maintain and iterate on the embodied AI data collection system: multimodal sensor synchronization, data pipelines, storage, and annotation toolchains.
- Own integration, calibration, and routine maintenance of camera systems (ZED, RealSense, industrial cameras) and robotic arms, ensuring equipment stability and uptime.
- Independently deploy imitation learning, DAgger, and teleoperation algorithms on robots, including data collection, model training, inference deployment, and on-site tuning.
- Drive data quality assurance: timestamp synchronization, coordinate frame alignment, anomalous data detection, and rapid diagnosis of collection failures.
- Define and maintain robot-side software interfaces and communication protocols (ROS2, DDS) to enable fast replication across platforms and sites.
- Support on-site data collection and algorithm deployment, produce technical documentation, and continuously improve collection efficiency and model performance.
You will work in a flat, open engineering culture with genuine involvement in technical decisions, well-equipped hardware lab resources, and flexible work arrangements.
Requirements:
- Bachelor's degree or above in Robotics, Automation, Computer Science, or related field, with 3+ years of relevant experience.
- Strong programming skills in Python and C++; system-level development and debugging in Linux environments.
- Expert in ROS/ROS2, including node communication (Topics, Services, Actions), parameter management, and Launch system.
- Hands-on experience with camera system integration and calibration (intrinsics, extrinsics, multi-camera synchronization); familiarity with ZED, RealSense, or similar RGB-D/stereo cameras.
- Experience with robotic arm control interfaces (UR, Franka, xArm, or in-house arms); understanding of driver layer, kinematics, and high-level API calls.
- Familiarity with common robot hardware interfaces (CAN, EtherCAT, RS485, USB) and sensor integration (IMU, depth cameras, force/torque sensors).
- Experience training and deploying deep learning models; proficiency in PyTorch with ability to handle full workflow from data preparation through inference and deployment.
- Proficiency with AI coding tools (Claude Code, Cursor) in daily development, with demonstrated ability to boost engineering productivity.
Nice to Have:
- Complete project experience in embodied AI/imitation learning data collection and algorithm deployment.
- Familiarity with Diffusion Policy, ACT, and VLA algorithms.
- Knowledge of robot data formats (SVO2, ROS bag, HDF5, LeRobot datasets).
- Experience with multi-device synchronization (camera hardware triggering, PTP time synchronization).
- Integration experience with VIVE Trackers, OptiTrack, motion capture gloves.
- Video encoding/decoding experience (H.264, H.265, Jetson hardware codecs).
- Fluency in written English for reading research papers and open-source documentation.
