Machine Learning Architect, Platform Architecture

Apple • Cupertino, CA

3d

About The Position

Apple’s Platform Architecture group connects hardware and software into a unified system. The team works at the intersection of machine learning applications and Apple silicon architecture, collaborating with SoC/IP architecture, system, software, and algorithm teams to develop integrated, highly optimized solutions for machine learning applications.

In this role, you will explore ways to map machine learning workloads to Apple silicon and develop performance models and simulations to inform and validate architecture decisions. You will evaluate machine learning model optimization techniques from the literature through analysis and experimentation, identify what works and why, and propose new ideas. You will provide guidance to software and algorithm teams on making workloads run efficiently on Apple SoCs, and create optimized implementations for the Neural Engine, GPU, and CPU.

Requirements

• Bachelor’s degree.
• Experience in C/C++ and/or Python.
• Experience with hardware IPs such as machine learning hardware accelerators, GPU/CPU, image/video processors, or similar.
• Experience with machine learning frameworks (e.g., PyTorch) and efficient implementations of machine learning algorithms.
• 20+ years of relevant experience.
• Experience optimizing and deploying machine learning models and/or runtime frameworks in production inference/training environments.
• Experience designing experiments to evaluate machine learning model optimization techniques.
• Ability to prototype algorithms on CPU/GPU/Neural Engine, analyze performance metrics, and create high-level complexity models.
• Verbal and written communication skills for collaborating with partner teams.
• Understanding of compilers.

Nice To Haves

• MS or PhD in EE/CE/CS or a related field.

Responsibilities

• Map machine learning workloads to Apple silicon and develop performance models and simulations to inform and validate architecture decisions.
• Create optimized implementations of machine learning workloads on Apple silicon, including the Neural Engine, GPU, and CPU.
• Collaborate with IP and SoC architecture teams to develop performance models and simulations of future hardware.
• Collaborate with system teams to create high-level performance models of emerging machine learning techniques and analyze system architecture trade-offs.
• Evaluate emerging machine learning model optimization techniques through experimentation and analysis, and propose new ideas to inform hardware and algorithm direction.
• Provide guidance to software and algorithm teams on efficient workloads for Apple SoCs.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior