ML Software Engineer

Apple's Machine Learning and AI team is seeking a ML Software Engineer to join their Private Cloud Compute component of Apple Intelligence. The role focuses on building ML-inference applications and services on Apple Silicon in the datacenter, with recent emphasis on generative AI. As part of this highly skilled team, you'll work on engineering continuous improvements in stability and performance for private cloud compute, while implementing cutting-edge functionality emerging from the research community.

The position involves writing performant and scalable frameworks in Swift and C++ to distribute and coordinate ML inference tasks across different hardware acceleration IP blocks on various SoCs. You'll be joining a team of domain experts who specialize in specific core subject areas while maintaining broad experience in cloud software services and platforms.

The ideal candidate should have strong experience in software engineering on large production systems, proficiency in Swift, C, C++, and iOS/macOS development, and practical experience with machine learning models. Knowledge of Apple's ML stack (ANE, CoreML, MPS/Metal) and distributed ML systems is a plus.

This role offers competitive compensation ranging from $135,400 to $250,600, comprehensive benefits including medical coverage, retirement benefits, and various stock programs. You'll have the opportunity to work on cutting-edge technology while collaborating with product teams throughout Apple, making a direct impact on the company's AI and machine learning initiatives.