On-device ML Infrastructure Engineer
Core
Develop and improve core runtime infrastructure for machine learning model execution across Apple devices, focusing on execution stability, performance, and optimization.
Role type
Senior IC machine learning infrastructure engineer (on-device)
Builds
Core runtime infrastructure, model orchestration capabilities, and tooling for efficient ML model execution on Apple hardware.
Domain
Consumer electronics / Machine Learning Infrastructure
Deliverable
production ML models
Required skills
Python 3, C++, Swift, machine learning model architectures, PyTorch, kernel development, profiling, benchmarking, debugging
Preferred skills
MLIR-based compilers, Apple platform deployment, GPU/CPU/Neural Engine programming paradigms, kernel writing for ML execution
Technologies
Python, C++, Swift, PyTorch, MLIR, Neural Engine, GPU, CPU
Responsibilities
Develop and improve core runtime infrastructure for ML model execution; Build model orchestration capabilities; Collaborate with model authoring, compiler, and runtime teams; Support model optimization, transformation, debugging, profiling, and benchmarking; Write kernels and contribute to tooling for efficient ML model execution.
Seniority
Mid-level, hands-on IC
