5 months ago
Base Salary
$180k - $300k/yr
Responsibilities
- Design and optimize hand and full-body pose estimation systems for teleoperation, motion capture, and robot training annotations.
- Develop camera intrinsic/extrinsic calibration, hand-eye calibration, visual SLAM, scene reconstruction, and multimodal sensor synchronization pipelines.
- Train, evaluate, and deploy perception models for object detection, instance segmentation, and 6DoF pose estimation.
- Optimize real-time embedded inference using TensorRT and CUDA, including custom CUDA kernels.
- Build automated annotation and Auto QA pipelines and connect perception quality metrics to downstream model training outcomes.
Requirements
- 5+ years of industry experience in robot perception or computer vision.
- Strong 3D vision fundamentals, including stereo cameras, structured-light cameras, and 3D reconstruction.
- Proficiency with SLAM frameworks such as ORB-SLAM, VINS-Mono, or FastLIO, or experience developing V-SLAM systems.
- Hands-on experience with human pose estimation using hand-joint or full-body pose methods and tools such as MediaPipe, MANO, OpenPose, or SMPLify.
- Experience training, tuning, and evaluating deep-learning perception models.
- TensorRT deployment and real-time inference optimization experience on embedded platforms such as Jetson or Horizon.
- CUDA programming fundamentals, including the ability to write or debug custom kernels.
- Proficiency in C++, Python, and ROS/ROS2 development.
- Proficiency with AI coding agents.
- Preferred qualifications include 6DoF object pose estimation, 3D Gaussian Splatting or NeRF, robot manipulation or teleoperation, automated annotation or ground-truth systems, and published perception, pose-estimation, or robotics research.
Benefits
- Direct involvement in producing high-quality robot training data for embodied intelligence.
- Work alongside robotics engineers and ML researchers.
- Access to proprietary hardware platforms including humanoid robots, camera arrays, and data gloves.
- Fast-paced, high-autonomy 0→1 work environment.
About XDOF
XDOF builds data, software, and operational infrastructure for robotics companies and research labs developing general‑purpose robots and physical AI. It provides scalable data collection, tooling, hardware integration, and services that help teams train, deploy, and manage autonomy systems. The company is privately held and positions itself as an infrastructure partner to frontier labs and robotics builders, with a team drawing experience from Tesla, Google, Applied Intuition, BAIR, Covariant, and Gatik.