Computer Vision ML / Research Engineer

About the Role

Join a computer vision team building an industrial inventory measurement system using stereo camera data. You will own the core perception pipeline, turning real-world captures into accurate, auditable 3D pile measurements that support the product's measurement capabilities.

What You'll Do

• Build and improve stereo reconstruction, depth estimation, segmentation, and point-cloud processing workflows.

• Develop ground-plane estimation, point-cloud cleanup, stitching, and 3D volume calculation methods.

• Integrate and evaluate computer vision models, including stereo and YOLO-style models.

• Assess reconstruction quality and volume accuracy, and investigate failure modes using real-world sensor data.

• Define calibration assumptions and develop confidence metrics for measurement outputs.

• Move research-stage perception workflows toward reliable, production-ready systems.

What We're Looking For

• At least 4 years of directly relevant work or research experience in computer vision, machine learning, or perception.

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

• Hands-on experience with stereo vision, depth estimation, point clouds, camera calibration, or 3D reconstruction.

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

• Robotics perception, autonomous systems, CUDA, SLAM, photogrammetry, or industrial inspection experience is useful.

• Graduate study in computer vision, robotics, or a related field is a plus.

Compensation & Benefits

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

Location

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