On-device Machine Learning Infrastructure Engineer (Compiler & Runtime)

The On-Device Machine Learning team at Apple is seeking a skilled ML Infrastructure Engineer to join their team focused on graph compilers and runtimes. This role is central to Apple's machine learning initiatives, working on infrastructure that powers experiences across Camera, Siri, Health, and Vision platforms. The position involves building the world's leading ML graph compilation and runtime system for optimizing and executing ML models on Apple products.

The role focuses on developing graph compilers that optimize ML graphs from popular frameworks like PyTorch, JAX, and MLX for efficient execution on Apple Silicon. You'll be instrumental in creating the first end-to-end developer experience for ML development, leveraging Apple's vertical integration. The position requires expertise in ML operator primitives, compiler optimizations, runtimes, and system software engineering.

As part of the team, you'll work on critical infrastructure that handles everything from onboarding new ML architectures to embedded devices, optimization toolkits, and debugging toolchains. This is an opportunity to impact Apple's ML workflows across multiple product lines while working with cutting-edge technology and cross-functional teams.

The ideal candidate will have strong C++ programming skills, understanding of ML fundamentals, and experience with compiler stacks. Additional experience with ML frameworks, GPU programming, and on-device ML stacks would be advantageous. This role offers competitive compensation, including base pay, stock options, and comprehensive benefits, making it an excellent opportunity for those passionate about ML infrastructure and system-level optimization.