4 hours ago
Base Salary
$150k - $200k/yr
Responsibilities
- Build perception systems for detection, classification, tracking, temporal understanding, and 3D vision.
- Address first-person vision challenges including camera motion, changing viewpoints, occlusion, motion blur, and variable lighting.
- Use field failures to improve models, data, and evaluation.
- Develop geometric vision capabilities including calibration, localization, pose estimation, and coordinate transformations.
- Train and debug PyTorch models using synthetic and real-world data.
- Optimize low-latency inference and deploy perception systems on edge hardware in factory environments.
- Lead underspecified problems end to end and work directly with users or in field deployments.
Requirements
- At least 3 years of experience building and deploying computer vision, robotics perception, or applied ML systems outside notebooks or lab settings.
- Experience shipping reliable real-time perception systems for changing real-world conditions.
- Strong Python, PyTorch, and OpenCV skills, including development and debugging of detection, classification, or tracking models.
- Experience with geometric vision and edge deployment or production inference optimization.
- Technical ownership and judgment to lead underspecified problems end to end.
- Experience with synthetic data, Sim2Real, SLAM or VIO, depth or 3D reconstruction, CUDA or TensorRT, ROS2, or robot learning is a plus.
Benefits
- Annual salary range of $150,000 to $200,000 USD.
- Visa sponsorship is available.
- On-site role in San Francisco, California.