The ML Infrastructure Engineer role focuses on model compilation within the On-Device Machine Learning team at Apple. This team is dedicated to transforming innovative AI research into practical applications for Apple devices. The position involves collaborating with model authoring, runtime, and performance teams to optimize machine learning models for hardware capabilities. The engineer will contribute to building an end-to-end developer experience for machine learning development across various Apple platforms.

• 3-5 years of experience working on MLIR-based compilers.
• Familiarity with common ML model architectures, execution schemes, and operations.
• Proficiency in C++ programming language.
• Experience with PyTorch or related training frameworks.
• Familiarity with Swift programming language.
• Knowledge of programming paradigms for the GPU, CPU, and Neural Engine.
• Experience in writing kernels for ML model execution.

• Work closely with model authoring, runtime, and performance teams to ensure optimal model execution.
• Develop and maintain the core runtime for machine learning execution across various devices.
• Contribute to the optimization of machine learning models for performance and efficiency.
• Assist in building comprehensive benchmarking and debugging toolchains for machine learning workflows.
• Collaborate with cross-functional teams to enhance the developer experience for machine learning development.

• 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.