Description
Apple is hiring an On-device ML Performance Engineer to analyze and optimize the performance, memory, power, and numerical correctness of machine learning models running on Apple Silicon devices. The role covers on-device inference analysis, model conversion and compilation optimization, development of performance and debugging tools, and collaboration across research, software, hardware, and product teams. Candidates should have experience with ML inference, quantization, model architectures, computer architecture, embedded systems, and Python/C++ and shell scripting.
