The On-device Machine Learning Performance Engineer will work within Apple's On-Device Machine Learning team, focusing on optimizing the performance of machine learning models on Apple hardware. This role involves deep analysis of ML models, ensuring they run efficiently on Apple Silicon. The engineer will collaborate with various teams to enhance the ML software stack and leverage advanced techniques for performance optimization. A passion for machine learning and a strong technical background in computer architecture are essential for success in this position.

• Technical expertise in computer architecture, performance, memory, and power.
• Experience with ML model architectures and frameworks such as PyTorch.
• Familiarity with operating systems, embedded systems, and CPU/GPU/SoC architectures.
• Highly proficient in Python, C++, and shell scripting.
• Exceptional clarity in verbal and written communication.
• Masters or PhDs in Computer Science or relevant disciplines.

• Analyze and optimize the performance of ML models on iPhones and Macs.
• Implement ML models in the software stack for optimum performance, power, and memory usage.
• Debug performance and power consumption issues across CPU, GPU, and Apple Neural Engine.
• Generate utilities and debug tools to extract and report performance metrics.
• Explore and learn about the latest advances in ML model design and architecture.

• Employees at Apple are often offered comprehensive benefits that support physical and mental well-being—flexible medical plans, confidential counseling, onsite wellness centers at major campuses, and resources for fitness and daily life. Families typically receive fertility support, paid parental leave with gradual return, caregiving leave, and dependent-care guidance, while financial perks commonly include stock grants (with purchase discounts), 401(k) matching, and income-protection coverage. Employees also see robust time off, Apple University learning and tuition reimbursement, donation matching and paid volunteer hours, and deep product and partner discounts.