Server ML Frameworks Engineer

Apple•Cupertino, CA

About The Position

Apple’s Server ML Frameworks team in Intelligent System Experience enables Apple Intelligence through high-performance, distributed inference of generative AI applications, including LLMs, on Private Cloud Compute. The team works on custom-built server hardware that brings the power and security of Apple silicon to the data center. The role is a senior technical leadership position responsible for setting the technical direction and software architecture for frameworks powering Apple Intelligence at scale. The engineer partners with teams across Apple to propose, develop, and evaluate features in new Apple Intelligence models; collaborates with hardware organizations to influence next-generation silicon design; and helps define compute and programming models for future server architectures. The role also includes growing and mentoring engineers, establishing engineering best practices, and building cross-functional relationships to deliver complex, multi-team initiatives. The work includes developing optimized GPU compute kernels across machine learning, image processing, linear algebra, and computer vision; defining and implementing APIs in Metal Performance Shaders; performing compiler- and kernel-level analysis and optimization; partnering with Platform Architecture on the Apple GPU compute hardware roadmap; analyzing performance on future silicon; and tuning GPU-accelerated compute across products.

Requirements

Bachelor’s, master’s, or Ph.D. in Computer Science or a related field, or equivalent practical experience.
3–5 years of experience as a manager or technical leader.
Experience with GPU kernel development and optimization using compute programming models such as Metal, CUDA, or similar.
Experience with distributed training or inference techniques.
Strong system-level programming skills in C/C++, with a solid understanding of operating systems and computer architecture.
Track record in strategic leadership and decision-making.
Familiarity with Apple framework and API design patterns.

Nice To Haves

Experience with graph compilers such as CuTE, CuTile, Triton, OpenXLA, or LLVM.
Good understanding of LLM and diffusion-based model architectures.

Responsibilities

Set the technical direction and software architecture for frameworks powering Apple Intelligence at scale.
Partner with teams across Apple to propose, develop, and evaluate features in new Apple Intelligence models.
Collaborate with hardware organizations to influence the design of next-generation silicon.
Help define compute and programming models for future server architectures.
Grow and mentor a team of engineers, establish engineering best practices, and build cross-functional relationships for complex multi-team initiatives.
Add optimized GPU compute kernels across machine learning, image processing, linear algebra, and computer vision.
Define and implement APIs in Metal Performance Shaders.
Perform in-depth analysis and compiler- and kernel-level optimizations to maximize performance across hardware families.
Partner with Platform Architecture teams to define the Apple GPU compute hardware roadmap.
Work with hardware teams to analyze performance on future silicon.
Tune GPU-accelerated compute across products.