Power-Efficient Embedded CPU Architect, Platform Architecture

Apple Inc.; Santa Clara (CA); On-site; USD 240,000 - 320,000; Full time

Job summary

Apple Inc. is seeking an Embedded CPU Performance Architect to define CPUs for embedded applications across iPhone, iPad, Mac, and other Apple products. You will model improvements balancing performance, power, and area, collaborating with designers to implement feasible solutions.

You will analyze workloads, correlate RTL with CPUs performance simulators, and help drive data-driven decisions to boost team productivity while tackling varied, challenging use cases.

Qualifications

• Experience in CPU and SOC architecture.
• Experience with performance simulation environments.
• OO programming in C/C++.
• Perl or Python scripting experience.
• Expertise in CPU microarchitecture areas: branch prediction, prefetching, pipeline optimization, datapath, memory hierarchy.
• 20+ years of industry experience.
• Understanding of data structures and algorithms.
• Familiarity with SIMD, vector, or accelerator architectures.
• Power-performance trade-offs in CPU designs and low-power design techniques.

Responsibilities

• Drive performance and efficiency optimization for embedded CPUs across Apple products.
• Collaborate with CPU designers to assess feasibility of ideas through modeling.
• Correlate RTL with performance simulators to ensure target meeting and model accuracy.
• Analyze workloads to identify bottlenecks and opportunities for improvement.

Skills

CPU architecture

Performance simulation

C/C++ OO

Perl/Python scripting

Branch prediction

SIMD/Vector

Data structures

Power optimization

20+ years experience

Education

MS/PhD in EE/CE/CS

Job description

Apple Inc. is seeking an Embedded CPU Performance Architect to define CPUs for embedded applications across iPhone, iPad, Mac, and other Apple products. You will model improvements balancing performance, power, and area, collaborating with designers to implement feasible solutions.

You will analyze workloads, correlate RTL with CPUs performance simulators, and help drive data-driven decisions to boost team productivity while tackling varied, challenging use cases.