Machine Learning Compiler Engineer

As a Machine Learning Compiler Engineer, you will be responsible for architecting and developing the compiler for Apple's proprietary Neural Engine Accelerator. This involves optimizing for deep learning inference, focusing on performance, scalability, and power efficiency. You will collaborate with cross-functional teams to support new hardware silicon and ensure compiler support for next-generation features. Leading the design and implementation of complex compiler features is crucial, as is mentoring engineers and defining new compiler architecture approaches. You will also identify initiatives to improve AI workload performance, contributing to the vision of the Apple Neural Engine team. Cultivating a culture of learning and collaboration is also part of the job responsibilities.