Description
The On-Device Machine Learning team is hiring an ML Infrastructure Engineer focused on model compilation. The role develops infrastructure for running machine learning models across Apple devices, including model authoring, runtime, optimization, transformation, execution, debugging, profiling, and analysis. It works with MLIR-based compilers targeting the neural engine, GPU, and CPU, and requires experience with MLIR-based compilers, C++, PyTorch or related frameworks, and familiarity with model architectures and execution schemes.
