Senior Computer Vision Engineer, Egocentric

This is a fully remote position, open to applicants in United States.

📋 Description

• Take charge of the early egocentric video and perception framework, encompassing data collection and camera rig setups, vision models, processing pipelines, and dataset delivery.

• Define and develop the data product across various quality tiers, including RGB egocentric video, depth-enhanced and multimodal capture, as well as hand pose, body pose, and annotations.

• Prioritize product development based on customer needs while ensuring high standards of data quality.

• Manage the selection of cameras and rigs, hardware installation, enrollment, edge processing, data ingestion, and production dataset pipelines.

• Collaborate with warehouse operations, engineering teams, and customers to meet specifications and deadlines.

• Create systems for detection, tracking, segmentation, depth/3D reconstruction, 6DoF, and multi-view 3D hand/body pose estimation.

• Construct VLM-assisted and automated labeling workflows, incorporating human-in-the-loop quality assurance.

• Lead efforts in camera calibration, epipolar and multi-view geometry, frame-accurate synchronization, and 3D pose triangulation.

• Design, fine-tune, optimize, and implement computer vision and multimodal models on extensive, unstructured video datasets.

• Develop reproducible production systems and assist in the operationalization and scaling of the new physical AI data enterprise.

⛳️ Requirements

• Over 8 years of experience in building and delivering production computer vision/perception systems, or an MS/PhD in computer vision, ML, or robotics with at least 6 years of practical industry experience.

• Proven experience in constructing and scaling an egocentric perception or video data stack from start to finish.

• Ideally, experience within the fields of robotics, physical AI, or an AI data organization.

• In-depth knowledge of detection, tracking, segmentation, depth, 2D/3D pose estimation, and vision transformers.

• Strong understanding of geometric computer vision principles, including camera calibration, multi-view geometry, synchronization, and 3D reconstruction.

• Demonstrated ownership of perception challenges from data and model design through to evaluation, optimization, and deployment.

• Experience managing large, unstructured video and multimodal datasets along with a disciplined approach to evaluation and quality measurement.

• A proven track record of setting technical direction and enhancing the standards for fellow engineers.

• Capability to navigate ambiguous 0→1 challenges from concept to operational system with limited resources.

• Expert-level proficiency in Python and a solid foundation in software engineering principles.

• Experience with C++ where performance requirements are critical.

• Must possess authorization to work in the U.S.

🏝️ Benefits

• Competitive salary and comprehensive benefits package.

• Opportunities for professional development and growth.

• Collaborative and innovative work environment.

• Flexible work arrangements to support work-life balance.