Skip to main content

On-Device ML Infrastructure Engineer (Core AI Runtime), Graphics, Games and Machine Learning

Posted today

appleCupertino (CA)

SENIORITY

Manager

Apply (opens in a new tab)

About the role

Overview: In this role you will advance the Core ML Runtime to run ML models efficiently on Apple devices. You’ll join a cross-disciplinary team shaping on-device ML infrastructure that powers Camera, Siri, Health, Vision, and more. You’ll tackle graph compilation, runtimes, and system software to deliver private, high-performance AI at scale. This is a chance to influence ML workflows across Apple platforms and contribute to a mission of private, efficient computation. Compensation / Benefits Comprehensive medical and dental coverage Retirement benefits Discretionary stock programs Education expense reimbursement Relocation assistance Discounted products and free services
Responsibilities: Build and optimize a world-class ML graph compilation and runtime system for on-device execution Develop and maintain the end-to-end developer experience for model authoring, optimization, transformation, and profiling within Apple's stack Contribute to operator primitives, compiler optimizations, and runtime components to improve performance and efficiency Collaborate with cross-functional teams across hardware, software, and product groups to enable scalable ML workflows on Apple devices Work on embedding OS-level parallelism and system software aspects relevant to ML workloads
Key requirements: Master's degree or equivalent in Computer Science, Engineering, or related field Proficiency in C++ or Swift; familiarity with Python Experience with any compiler stack (MLIR/LLVM/TVM, etc.) Knowledge of operating systems, embedding programming, and parallel programming Solid understanding of ML fundamentals and architectures (e.g., Transformers) Strong communication skills for cross-functional collaboration creative versatile strong communicator C++/Swift programming Python ML compiler stacks (MLIR, LLVM, TVM)

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