<p>The Video Computer Vision organization is working on breakthrough technologies for future Apple products. Our team delivers cutting-edge AI, machine learning, computer vision and graphics algorithms that power technologies including human understanding, perception, digital humans, AI agents and health applications. In this role, you will collaborate with world-class experts in AI, ML, Software, and Hardware to tackle fundamental challenges in human-centric solutions that will impact millions of users across Apple's ecosystem.We are looking a CVML Engineer with deep expertise in multi-view geometry and modern machine learning approaches. In this role, you will research, adapt, and implement state-of-the-art 3D and 4D reconstruction algorithms for human understanding and AI health applications, designing novel approaches that combine classical geometry with modern deep learning techniques. You will collaborate with cross-functional teams to define requirements and validation frameworks. You will deliver production-ready code while driving technical innovation for health and human intelligence applications and optimize algorithms for deployment on Apple silicon on mobile devices. The ideal candidate will demonstrate passion for pushing the boundaries of 3D and 4D computer vision, possess a strong applied research mindset with ability to translate academic innovations into shipping products, bring a collaborative approach to solving complex technical challenges, and maintain commitment to engineering excellence and clean, maintainable code.MS or PhD in computer vision, computer graphics, machine learning, computer science, computer engineering or related fields.</p> <p>Experience with human-centric 3D and 4D reconstruction approaches, datasets and evaluation methodology.</p> <p>Deep understanding of multi-view geometry, camera calibration and 3D reconstruction pipelines.</p> <p>Background in differentiable optimization and geometric deep learning approaches.</p> <p>Experience optimizing ML models for mobile deployment and resource-constrained environments.</p> <p>Knowledge of SLAM, bundle adjustment and photogrammetric reconstruction techniques.Array</p>