27 days ago
Remote, United States or Atlanta, GA, USASenior
Responsibilities
- Own the egocentric video and perception stack from data collection and camera rigs through vision models, processing pipelines, and dataset delivery.
- Define and build data products spanning RGB video, depth-enhanced capture, multimodal capture, hand and body pose, and annotations.
- Select, configure, enroll, and operate camera and rig hardware while managing edge processing, data ingestion, and production dataset pipelines.
- Develop detection, tracking, segmentation, depth and 3D reconstruction, 6DoF, and multi-view 3D hand and body pose estimation systems.
- Build VLM-assisted and automated labeling workflows with human-in-the-loop quality assurance.
- Drive camera calibration, epipolar and multi-view geometry, frame-accurate synchronization, and 3D pose triangulation.
- Design, fine-tune, optimize, and deploy computer vision and multimodal models on large unstructured video datasets.
- Set technical direction and operationalize reliable production systems for a new physical AI data business.
Requirements
- 8+ years building and shipping production computer vision or perception systems, or an MS/PhD in computer vision, machine learning, or robotics with 6+ years of hands-on industry experience.
- Experience building and scaling an egocentric perception or video data stack end to end, ideally in robotics, physical AI, or an AI data company.
- Deep expertise in detection, tracking, segmentation, depth, 2D/3D pose estimation, and vision transformers.
- Strong command of camera calibration, multi-view geometry, synchronization, and 3D reconstruction.
- Experience owning perception problems from data and model design through evaluation, optimization, and deployment.
- Experience with large unstructured video and multimodal datasets and disciplined evaluation and quality measurement.
- Track record of setting technical direction and raising the bar for other engineers.
- Ability to take ambiguous 0-to-1 problems from concept to working systems with limited resources.
- Expert-level Python and strong software engineering fundamentals; C++ experience where performance requires it.
- Comfort working across hardware, data, models, infrastructure, and operations.
Benefits
- 0-to-1 ownership of the product, technology, team, and operating model for a new physical AI data business.
- Direct access to large-scale real-world warehouse environments, workflows, and human activity for training data.
- Direct partnership with the CTO and co-founder on the technical and commercial direction of the business.
Categories
ML EngineeringRobotics
