GPU Software Architecture Engineer

Who you are

You have a strong background in GPU software architecture and a deep understanding of machine learning systems — your experience includes leading initiatives that optimize GPU compute infrastructure for large-scale applications. You are skilled in designing sophisticated parallelization strategies and have a proven track record of orchestrating complex distributed systems. Your expertise in performance profiling and optimization techniques allows you to tackle unprecedented scaling challenges effectively.

You thrive in collaborative environments, working closely with silicon architects and cross-functional teams to influence future GPU designs based on your insights into inference workload characteristics. You are passionate about building production systems that serve billions of requests daily, ensuring maximum hardware utilization while minimizing latency for real-time user experiences.

Your technical leadership experience has equipped you with the ability to dive deep into performance issues and implement novel solutions that enhance system efficiency. You are committed to staying at the forefront of technology, continuously learning about emerging approaches in GPU architecture and machine learning.

Desirable

Experience with private cloud computing and familiarity with Apple’s ecosystem would be advantageous. A background in AI experiences and a strong understanding of secure cloud infrastructure will set you apart.

What you'll do

In this role, you will lead the architecture and development of next-generation distributed ML infrastructure — your work will involve defining and shaping GPU compute systems that enable Apple Intelligence. You will tackle the complex challenges of orchestrating massive network models across server clusters, ensuring that the infrastructure can handle unprecedented scale.

You will design and implement sophisticated parallelization strategies that split models across multiple GPUs, optimizing every layer of the stack from low-level memory access patterns to high-level distributed algorithms. Your focus will be on achieving maximum hardware utilization while minimizing latency, which is crucial for delivering real-time user experiences.

As a hands-on technical leader, you will not only architect these systems but also engage in performance profiling and implement optimization techniques that drive efficiency. You will collaborate with silicon architects to influence future GPU designs, ensuring that they meet the demands of advanced machine learning workloads.

Your role will also involve mentoring junior engineers and fostering a culture of innovation within the team. You will be responsible for defining best practices in GPU software architecture and ensuring that the team adheres to these standards.

What we offer

Apple provides a dynamic work environment where innovation is at the core of everything we do. You will have the opportunity to work on cutting-edge technologies that impact millions of users worldwide. We offer competitive compensation and benefits, along with a culture that values diversity and inclusion. Join us in shaping the future of AI experiences through our secure cloud infrastructure.