Skip to main content

Machine Learning Compute Efficiency Lead, Infrastructure & Planning

Posted yesterday

appleCupertino (CA)

SENIORITY

Manager

Apply (opens in a new tab)

About the role

Overview: In this role you will drive the efficiency and scalability of Apple’s ML inference compute, partnering with ML engineering and infrastructure teams to optimize resource use and reduce serving costs. You will design and implement strategies for large-scale model serving across GPUs, TPUs, and custom silicon, aligning with Apple’s mission to empower AI experiences at scale. The role combines hands-on optimization with cross-org leadership to influence platform decisions and enable performant, cost-effective AI at hundreds of millions of users. This is a high-impact opportunity to shape the foundation of Apple Intelligence through efficient infrastructure. Compensation / Benefits base pay range Apple stock programs restricted stock unit awards Employee Stock Purchase Plan comprehensive medical and dental coverage retirement benefits
Responsibilities: Own and support ML compute management for inference workloads across GPU, TPU, and custom silicon to enable large-scale model serving Collaborate with Apple Intelligence and ML engineering teams to understand roadmaps and resource pain points to develop resource strategies Optimize ML workloads by improving performance, maximizing resource utilization, and reducing service costs via deep root-cause analysis that informs engineering decisions and user experience Architect solutions for large-scale optimization including capacity allocation, workload scheduling, and cost reduction for Apple’s AI-driven experiences Advocate for ML engineers to align ML platform and inference requirements with internal infrastructure providers and public cloud partners
Key requirements: 7+ years in ML infrastructure, systems architecture, or efficiency/optimization roles at scale Strong conceptual understanding of foundation model inference/serving at scale and distributed training (data/tensor/pipeline parallelism), GPU/TPU utilization, memory hierarchies, and cluster scheduling AI-fluent and capable of quickly adapting to AI workflows and empowerment Proven track record of driving complex cross-org technical initiatives through influence, not authority Strong analytical skills with experience designing or interpreting utilization analyses, capacity models, or efficiency metrics Clear written and verbal communication, comfortable presenting to VPs and white-boarding with senior ML engineers cross-functional collaboration effective communication influence without authority foundation model serving/inference at scale distributed training (data/tensor/pipeline parallelism) GPU/TPU utilization

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.

More like this