This role requires an independent, self-motivated, and creative engineer with deep expertise in machine learning, coupled with a strong understanding of video and image processing quality. Your primary focus will be applying cutting-edge machine learning techniques to complex image and video challenges to create customer impact across current and future Apple products. In this role, you’ll work both independently and collaboratively with team members to prototype innovative deep learning applications for video processing, presenting and demonstrating your work to cross-functional teams and leadership alike. You’ll be responsible for designing sophisticated model architectures, fine-tuning performance parameters, and implementing architectural modifications to enhance overall output quality. Working closely with the team, you’ll focus on seamlessly porting solutions across different platforms while optimizing models for memory efficiency, power consumption, and processing speed to balance quality in operating constraints. Additionally, you’ll strategically distribute computational workloads across CPU, GPU, Apple Neural Engine, and other specialized hardware components to develop robust, viable solutions.