On-Device ML Infrastructure Engineer, CoreML Runtime

What you'll do

• Architect and maintain the on-device graph compiler, runtime, and kernels for ML operators.
• Develop production-critical system software to implement machine learning models on Apple Silicon.
• Optimize model execution for performance, energy efficiency, and thermal management.
• Build an end-to-end developer experience for model authoring, optimization, and execution.
• Develop optimization toolkits for model compression and acceleration.
• Build ML compilers and runtimes for efficient execution on resource-constrained devices.
• Create comprehensive benchmarking and debugging toolchains for machine learning workflows.
• Identify and resolve functionality gaps in the Core ML Runtime.

What we're looking for

• Master's degree or equivalent experience in Computer Science, Engineering, or a related subject area.
• High proficiency in C++ or Swift.
• Familiarity with Python.
• Experience with any compiler stack such as MLIR, LLVM, or TVM.
• Familiarity with operating systems, embedded programming, and parallel programming.
• Sound understanding of ML fundamentals, including common architectures such as Transformers.
• Experience with any on-device ML stack such as TFLite, ONNX, or ExecuTorch (preferred).
• Experience with ML authoring frameworks like PyTorch, TensorFlow, or JAX (preferred).