Senior Computer Vision ML / Research Engineer

About the Role

Own the computer vision and perception pipeline that turns stereo camera captures into accurate, auditable measurements of industrial inventory. You will work at the center of the product, taking core 3D vision and measurement capabilities from research through production.

What You'll Do

• Build and improve stereo reconstruction, depth estimation, segmentation, point-cloud cleanup, ground-plane estimation, stitching, and 3D volume calculation.

• Integrate models such as FoundationStereo, S2M2, and YOLO-style systems into the perception pipeline.

• Evaluate reconstruction quality and measurement accuracy, investigate failure modes, and develop confidence metrics.

• Validate calibration assumptions and debug real-world sensor data to make the system reliable in production.

• Move research pipelines toward production-grade measurement systems.

What We're Looking For

• At least 4 years of experience in computer vision or perception machine learning engineering, including shipping computer vision systems that use real-world sensor data.

• Relevant work or research experience in stereo perception, point clouds, 3D reconstruction, or volume measurement.

• Strong Python, PyTorch, and 3D geometry skills, with experience using OpenCV and Open3D.

• Practical knowledge of stereo vision, camera calibration, depth estimation, segmentation, and point-cloud processing.

• Experience in robotics perception, autonomous vehicles, industrial inspection, photogrammetry, SLAM, geospatial measurement, or volumetric measurement is useful.

• CUDA or GPU cloud experience, including Modal, is a plus; an advanced degree in computer vision, robotics, or a related field is also valued.

Compensation & Benefits

Annual salary range: $180,000 to $245,000 USD. Visa sponsorship is available.

Location

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