On-Device ML Orchestration & Performance Engineer

Apple, Inc.; Cupertino (CA); On-site; USD 150,000 - 278,000; Full time

Benefits offered by this job

Medical and dental

Retirement benefits

Employee stock purchase plan

Tuition reimbursement

Job summary

Apple's On-Device Machine Learning team in Cupertino seeks an ML Infrastructure Engineer focused on model orchestration and performance. You will collaborate with model authoring, compiler, and runtime teams to enable efficient, private execution of sophisticated ML models across Apple devices.

You will contribute to MLIR-based tooling and runtimes, optimize deployment across Apple Silicon, and help scale ML workflows for Camera, Siri, Health, and Vision.

Qualifications

• Experience with Python 3 and C++/Swift tooling for ML workflows.
• Familiarity with ML model architectures and execution schemes.
• Experience with PyTorch or related training frameworks.

Responsibilities

• Drive full-stack changes through the OS and tooling to enable deploying large SOTA models across the Apple Silicon ecosystem.
• Partner with teams across the company to support advanced use cases for Siri, Apple Intelligence, Camera, and more.
• Make changes in our authoring and MLIR-based compiler to expose mechanisms for state-of-the-art model execution.
• Implement mechanisms to support efficient orchestration of models across Apple Silicon hardware.

Skills

Python 3 & C++/Swift tooling

ML model architectures familiarity

PyTorch familiarity

Tools

MLIR-based compiler

Job description

Apple's On-Device Machine Learning team in Cupertino seeks an ML Infrastructure Engineer focused on model orchestration and performance. You will collaborate with model authoring, compiler, and runtime teams to enable efficient, private execution of sophisticated ML models across Apple devices.

You will contribute to MLIR-based tooling and runtimes, optimize deployment across Apple Silicon, and help scale ML workflows for Camera, Siri, Health, and Vision.