Embedded CPU Performance Engineer, Platform Architecture

Apple•Beaverton, OR

About The Position

Do you get more energy from the hardest problem in the room than the easiest one? Do you want a hand in shaping the CPUs that run quietly inside nearly every Apple product from the one your iPhone relies on to capture the perfect photo, to the one guarding your Apple Watch? The CPU Platform Architecture team exists to push the limits of power-efficient CPU performance, and we hold ourselves to a standard most teams wouldn’t bother with. We’re a tight-knit group obsessed with squeezing every drop of performance out of every milliwatt, bringing together deep expertise in microarchitecture, ISA definition, performance modeling, power modeling, and workload analysis. We’re looking for a highly motivated and innovative Embedded CPU Engineer to join us. In this role, you’ll drive performance and efficiency optimization and explore architectural features for Apple’s embedded CPUs that power critical functions across Apple’s entire product line. As an Embedded CPU Performance Engineer, you will help define CPUs that are specifically designed for running embedded applications across iPhone, iPad, Mac, and many other Apple products. Your focus will be to seek out areas for improvement in the unique constraints of varied embedded use cases, and model solutions that balance performance, power efficiency, and area. To do this you will collaborate with experienced CPU designers in micro-architecture and RTL to assess the feasibility of ideas through modeling and refine those ideas to make them implementable. You will also correlate RTL with the CPU performance simulator to ensure that the design meets targets and that the model is accurate. The role requires the analysis of specific workloads across a wide variety of existing and new product categories to identify bottlenecks and opportunities for improvement. We collaborate as a larger CPU architecture and performance team to maintain and improve the simulation and correlation environments to enable data driven decisions and look for ways to boost the productivity of the entire team.

Requirements

BS degree
Experience in CPU and SOC architecture and micro-architecture
Experience with performance simulation environments
Object-oriented programming skills in C/C++
Experience in a scripting language such as Perl or Python
Expertise in CPU microarchitecture in one or more of the following areas: branch prediction, prefetching, pipeline optimization, datapath, memory hierarchy
10+ years of relevant industry experience
MS or PhD in Electrical or Computer Engineering or Computer Science
Understanding of common data structures and algorithms
Familiarity with SIMD, vector, or accelerator architectures
Understanding of: power-performance trade-offs in CPU designs, system-level power management, and low-power design techniques
Comfortable in an environment of uncertainty and able to navigate through ambiguities
Experience in a research-driven environment

Responsibilities

Drive performance and efficiency optimization for Apple’s embedded CPUs.
Explore architectural features for embedded CPUs powering critical functions across Apple’s product line.
Define CPUs for embedded applications across iPhone, iPad, Mac, and other Apple products.
Identify areas for improvement in embedded use cases and model solutions balancing performance, power efficiency, and area.
Collaborate with CPU designers in micro-architecture and RTL to assess feasibility of ideas through modeling.
Refine ideas to make them implementable.
Correlate RTL with the CPU performance simulator to ensure design targets are met and the model is accurate.
Analyze specific workloads across various product categories to identify bottlenecks and opportunities for improvement.
Collaborate with the CPU architecture and performance team to maintain and improve simulation and correlation environments.
Enable data-driven decisions and seek ways to boost team productivity.