About the Role
Join an early engineering team at an industrial automation startup building computer vision systems for quality inspection in manufacturing. You will take perception from experimentation to reliable factory deployments, helping detect process issues early and laying groundwork for future robotic automation.
What You'll Do
Build perception systems for detection, classification, tracking, temporal understanding, and 3D vision.
Address first-person vision challenges such as camera motion, changing viewpoints, occlusion, motion blur, and variable lighting.
Work with the technical team to turn field failures into improvements to models, data, and evaluation.
Develop geometric vision capabilities including calibration, localization, pose estimation, and coordinate transformations.
Train and debug PyTorch models on synthetic and real-world data.
Optimize low-latency inference and deploy systems on edge hardware in factory environments.
What We're Looking For
At least 3 years building and deploying computer vision, robotics perception, or applied ML systems outside notebooks or lab settings.
Experience shipping real-time perception systems that perform reliably in changing real-world conditions.
Strong Python, PyTorch, and OpenCV skills, with experience developing and debugging detection, classification, or tracking models.
Experience with geometric vision and edge deployment or production inference optimization.
Technical ownership and judgment to lead an underspecified problem end to end, including working directly with users or in field deployments.
Experience with synthetic data, Sim2Real, SLAM or VIO, depth or 3D reconstruction, CUDA or TensorRT, ROS2, or robot learning is a plus.
Compensation & Benefits
Annual salary range: $150,000 to $200,000 USD. Visa sponsorship is available.
Location
On-site in San Francisco, California.