Senior Computer Vision ML / Research Engineer

About the Role

Join the perception team at an industrial computer vision company, building a system that uses stereo camera data to measure inventory piles accurately. You will own the core computer vision and machine learning pipeline, helping turn research methods into reliable, production-grade measurements.

What You'll Do

• Develop and improve stereo reconstruction, depth estimation, segmentation, and 3D volume estimation workflows.

• Integrate computer vision models and refine point-cloud cleanup, ground-plane estimation, and stitching.

• Evaluate reconstruction quality and volume accuracy using real-world sensor data.

• Review calibration assumptions, investigate failure modes, and develop confidence metrics for measurements.

• Move perception methods from research pipelines into production-ready systems.

What We're Looking For

• Approximately 4 to 10 or more years of relevant experience in computer vision, machine learning, or perception engineering.

• Strong Python and PyTorch skills, with hands-on experience using OpenCV or Open3D.

• Practical expertise in stereo vision, depth estimation, camera calibration, 3D geometry, point clouds, segmentation, or reconstruction.

• Experience shipping computer vision systems that use real-world sensor data, ideally including stereo perception or volume reconstruction.

• Experience in robotics or autonomous vehicle perception is valuable. CUDA, SLAM, photogrammetry, industrial inspection, and GPU cloud experience are also useful.

• A master's or doctoral degree in computer vision, robotics, or a related field is a plus.

Compensation & Benefits

Compensation is $180,000 to $245,000 USD annually. Visa sponsorship is available.

Location

On-site in San Francisco, California, United States.