Perception Algorithm Engineer

Apple is where individual imaginations gather together committing to the values that lead to great work. Every new product we build service we create or Apple Store experience we deliver is the result of us making each others ideas stronger. That happens because every one of us shares a belief that we can make something wonderful and share it with the world changing lives for the better. Its the diversity of our people and their thinking that inspires the innovation that runs through everything we do. When we bring everybody in we can do the best work of our lives. Here youll do more than join something youll add something. At Apple we strive to make great products that empower people and improve their lives. We believe recent breakthroughs in AI/ML and robotics have the potential to unlock new experiences that were never possible before and we are looking for talented Perception Algorithm Engineers to realize that mission by expanding the capabilities of Apple products and platforms.

As a member of the team youll have the opportunity to work with a team of highly skilled engineers and scientists to bring new experiences to Apple products. We are looking for a self-motivated algorithm engineer who is passionate about blending modern deep learning with robust classical techniques.

This position requires strong technical and interpersonal skills to handle responsibilities including:nDesigning and implementing a robust real-time multi-object tracking system to solve real-world computer vision multimodal estimates (vision audio etc.) to ensure robust high-fidelity estimation across complex and challenging rigorous evaluation frameworks curating datasets and defining metrics to benchmark model performance analyze edge cases and continuously improve perception perception systems into a larger software stack with real-world performance constraints.

PhD in Computer Science Robotics or MS with 3 years industry in systems programming (C/Swift) and writing performant production-quality in Python and modern ML frameworks (e.g. PyTorch JAX) with a solid foundation in machine learning and traditional perception and state-estimation to break down complex problems into testable solutions prioritizing challenging edge cases and accessible experiences for all about new technologies flexibility and an openness to ambiguity.

Experience designing scalable evaluation pipelines for learning based and classical perception in building and/or deploying on-device computer vision models or multi-object tracking area of particular domain expertise such as one of the following:nExperience with machine learning approaches and architectures (e.g. VLMs VLAs foundation models self-supervision distillation or data augmentation techniques).nExperience with classical and modern computer vision approaches reconstruction pipelines image processing/camera systems and computational photography pipelinesnExperience with multimodal data fusion across a variety of inputs and sensors including audio processing (e.g. DSP echo cancellation audio-visual diarization speech recognition)nKnowledge of the broader robotics software stack (e.g. kinematics planning controls) alongside state estimation methods (e.g. SLAM factor graphs filtering sensor fusion) and reinforcement learning applied math background (e.g. numerical optimization geometry graphics).nFamiliarity with Swift and Apple developer tools.