Staff Machine Learning Engineer : Platform Intelligence - Apple Maps

Apple Maps and the thousands of applications it empowers are being used by millions every single day! As a fundamental tool for human activity, Maps technology is evolving and new techniques are emerging.\\n\\nWe are looking for a Staff Machine Learning Engineer to drive the design, development, and deployment of machine learning models optimized for on-device training and inference. You will partner with a variety of subject experts across the company to build intelligent features and personalized maps experiences. This role involves collaborating with various partners, from engineers to designers, to architect the best overall system.\\n\\nIf you are excited about delivering intelligent, responsive, and personalized experiences to millions of users, we invite you to apply for the job and join us!\\n

Apple Maps Client is looking for a Staff Machine Learning Engineer to drive the design, development, and deployment of machine learning models optimized for on-device training and inference. Partnering with the Apple Neural Engine team to profile model performance, identify bottlenecks, and push the limits of what's possible on-device. Crafting technical design documents for new ML features is a core part of this role- outlining model architecture choices, performance targets, and deployment strategies.Your work includes building integration code that connects ML models with platform frameworks and APIs. You will lead cross-functional team projects.\n\nBeyond individual contributions, you will shape how the team approaches on-device ML. You will establish evaluation frameworks, define quality benchmarks, and write architecture documents that guide the team's direction. You will review code, mentor engineers, and help build a team culture rooted in technical rigor and collaboration.\n

Bachelor's in Computer Science, Machine Learning, Electrical Engineering, or a related field - or equivalent practical experience.\nStrong software engineering fundamentals in an object-orient programming language, with emphasis on writing production-grade, testable, and maintainable code.\nExperience with Systems Programming (frameworks/libraries/daemons).\n7+ years of industry experience in machine learning engineering, with at least 2 years focused on on-device/edge ML deployment.\nStrong proficiency in ML frameworks and tool chain such as PyTorch, TensorFlow, Core ML, Foundation Models Framework and MLX.\nProven track record of shipping ML models into production at scale on mobile or embedded platforms.

Master's, or PhD in Computer Science, Machine Learning, Electrical Engineering, or a related field - or equivalent practical experience.\nFamiliarity with Swift, and Objective-C.\nExperience building and operating end-to-end ML pipelines for on-device models - including training, evaluation, conversion, validation, A/B testing, and OTA model delivery.\nFamiliarity with federated learning, differential privacy, and on-device training/fine-tuning paradigms.