Description
The ML Infrastructure Engineer will work on Apple’s on-device machine learning infrastructure, focusing on model orchestration and performance across Apple Silicon devices. The role involves deploying large models, improving stability and performance, collaborating with model authoring, compiler, and runtime teams, and implementing mechanisms for efficient model orchestration. It requires 3–5 years of experience with Python 3 and C++/Swift tooling, familiarity with machine learning architectures and PyTorch or related frameworks, and preferably experience with MLIR-based compilers, Apple platforms, GPU/CPU/Neural Engine programming, and kernel development.
