CVML Engineer - 3D Reconstruction

Apple • Sunnyvale, CA

1d

About The Position

The Video Computer Vision organization develops computer vision, machine learning, and graphics algorithms for human understanding and geometric reasoning in health and fitness features. The CVML Engineer will research, adapt, and implement state-of-the-art 3D and 4D reconstruction algorithms for human understanding and geometry-driven health and fitness applications. The role combines classical geometry with modern deep learning to produce ground-truth data for training and evaluation and to develop robust runtime algorithms for on-device deployment. The engineer will collaborate with cross-functional AI, ML, software, and hardware teams to define requirements and validation frameworks, and deliver production-ready code optimized for Apple silicon and mobile devices.

Requirements

• Bachelor’s degree in Computer Vision, Machine Learning, Computer Graphics, or a related field.
• Hands-on experience developing 3D and/or 4D computer vision algorithms and systems, or equivalent experience.
• Deep understanding of multi-view geometry and 3D reconstruction pipelines.
• Strong proficiency in Python and PyTorch, with solid software engineering practices.
• Solid mathematical foundation in linear algebra, optimization, and geometry processing.
• Experience with modern machine-learning architectures and their applications to 3D problems.
• Excellent communication skills and ability to work effectively in cross-functional teams.
• Self-motivation and a track record of prioritizing effectively and delivering on schedule.

Nice To Haves

• Master’s or Ph.D. in Computer Vision, Computer Graphics, Machine Learning, Computer Science, or a related field.
• Experience with human-centric 3D and 4D reconstruction approaches, datasets, and evaluation methodology.
• Background in differentiable optimization and geometric deep-learning approaches.
• Experience optimizing machine-learning models for mobile deployment and resource-constrained environments.
• Knowledge of SLAM, bundle adjustment, and photogrammetric reconstruction techniques.
• Proficiency in C/C++.

Responsibilities

• Research, adapt, and implement state-of-the-art 3D and 4D reconstruction algorithms for human understanding and geometry-driven health and fitness applications.
• Design approaches combining classical geometry and modern deep learning to produce high-quality ground-truth data for training and evaluation.
• Develop robust, high-quality runtime algorithms for on-device deployment.
• Collaborate with cross-functional teams to define requirements and validation frameworks.
• Deliver production-ready code optimized for Apple silicon and mobile devices.

What This Job Offers

• Job Type: Full-time