Senior Perception Engineer — Robotics Vision & Data

xdof, Inc.; San Mateo (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Direct impact on robotics data

Collaborative environment

Proprietary hardware platforms

Job summary

XDOF invites a seasoned robot perception engineer to join our team in California. You will oversee the end-to-end perception pipeline—from data collection and calibration to model training and deployment on embedded platforms, directly impacting the quality of training data for our robotics systems.

You will develop 3D vision and pose estimation solutions, optimize inference with TensorRT, and collaborate with ML and data infrastructure teams to ensure downstream model training compatibility.

Qualifications

• 5+ years of industry experience in robot perception or computer vision.
• Strong 3D vision fundamentals: stereo and structured-light principles, 3D reconstruction.
• Proficiency with SLAM frameworks (ORB-SLAM, VINS-Mono, FastLIO, etc.) or V-SLAM system development.
• Hands-on engineering experience with human pose estimation: hand joints or full-body pose.
• Proficient in deep learning training frameworks for perception model training, tuning, and evaluation.
• TensorRT deployment experience with real-time inference optimization on embedded platforms.
• CUDA programming fundamentals; ability to write or debug custom kernels.
• Proficient in C++ and Python with ROS / ROS2 development experience.
• Proficient with AI coding agents.

Responsibilities

• Design and optimize hand pose estimation pipelines supporting accurate joint angle extraction from teleoperation data collection.
• Build full-body pose estimation systems for motion capture and teleoperation action annotation ground truth generation.
• Research and apply vision-based pose estimation methods to reduce data collection costs.
• Fuse pose estimation outputs with robot joint angle data to generate consistent training annotations.
• Design and maintain intrinsic/extrinsic calibration pipelines for multi-camera arrays.
• Build visual SLAM / V-SLAM systems for real-time localization and scene reconstruction on data collection platforms.
• Implement hand-eye calibration between cameras and robot end-effectors.
• Develop temporal alignment solutions across multimodal sensors.
• Train and iterate on perception models including object detection, instance segmentation, and 6DoF pose estimation.
• Optimize model inference using TensorRT for embedded platforms.
• Write custom CUDA kernels for acceleration of perception tasks.
• Design evaluation metric frameworks to track model performance vs data quality.
• Contribute to automated annotation pipelines that convert sensor data into structured training labels.
• Build Auto QA modules to filter low-quality data and anomalous frames.

Skills

Robot perception

3D vision

SLAM frameworks

Pose estimation

Deep learning for perception

TensorRT deployment

CUDA programming

C++ / Python / ROS

AI coding agents

Tools

ROS/ROS2

Job description

XDOF invites a seasoned robot perception engineer to join our team in California. You will oversee the end-to-end perception pipeline—from data collection and calibration to model training and deployment on embedded platforms, directly impacting the quality of training data for our robotics systems.

You will develop 3D vision and pose estimation solutions, optimize inference with TensorRT, and collaborate with ML and data infrastructure teams to ensure downstream model training compatibility.