On-device ML Infrastructure Engineer (Orchestration & Performance)
Core
Building end-to-end developer experience and core runtime infrastructure for executing machine learning models across Apple Silicon devices.
Role type
Senior IC ML Infrastructure Engineer (Orchestration & Performance)
Builds
ML compilers, runtimes, optimization toolkits, and benchmarking/debugging toolchains for Apple devices.
Domain
Consumer electronics / Machine Learning Infrastructure
Deliverable
production ML models
Required skills
Python 3, C++, Swift, ML model architectures, PyTorch, compiler optimizations, system software engineering
Preferred skills
MLIR-based compilers, Apple platform deployment, GPU/CPU/Neural Engine programming, kernel writing for ML execution
Technologies
Python, C++, Swift, PyTorch, MLIR, Apple Silicon
Responsibilities
Drive full-stack OS and tooling changes to deploy large SOTA models across Apple Silicon; Partner with teams to support advanced use cases for Siri, Apple Intelligence, and Camera; Modify authoring and MLIR-based compilers to expose mechanisms for state-of-the-art model execution; Implement mechanisms for efficient model orchestration across Apple Silicon hardware.
Seniority
Mid-Senior, hands-on IC
