Apple
On-device ML Infrastructure Engineer (Orchestration & Performance)
$150K–$278K
Cupertino, California · Full-time · Posted Sep 2, 2026
- Experience
- 3-5 years working on tooling built in Python 3 and C++/Swift.
About the job
Build and improve on-device ML runtime infrastructure to orchestrate and optimize model execution across Apple Silicon devices.
What you'll do
- Drive OS and tooling changes to deploy large models across Apple Silicon devices.
- Partner with company teams to support advanced use cases for Siri, Apple Intelligence, Camera, and more.
- Modify model authoring and the MLIR-based compiler, and implement efficient model orchestration across Apple Silicon hardware.
What they ask for
- Tooling experience with Python 3 and C++/Swift.
- Familiarity with common ML model architectures, execution schemes, and operations.
- Familiarity with PyTorch or related training frameworks.
Nice to have
- Experience with or adjacent to MLIR-based compilers; familiarity with deploying applications or tooling on Apple platforms.
- Familiarity with GPU, CPU, and Neural Engine programming paradigms or writing kernels for ML model execution.
Pay
$150,400 to $277,600 USD base salary
Tools
Python 3, C++, Swift, MLIR, PyTorch, Apple Silicon, GPU, CPU
AI focus
Develop infrastructure for deploying, orchestrating, and optimizing machine learning models on Apple devices.
Model-written summary · the original posting is authoritative