Hardware/Software Modeling and Validation Engineer

Summary

Apple is where individual imaginations gather together, committing to the values that lead to great work. Every new product we build, service we create, or Apple Store experience we deliver is the result of us making each other’s ideas stronger. That happens because every one of us shares a belief that we can make something wonderful and share it with the world, changing lives for the better. It’s the diversity of our people and their thinking that inspires the innovation that runs through everything we do. When we bring everybody in, we can do the best work of our lives. Here, you’ll do more than join something — you’ll add something. The Silicon Modeling and Development Team in the Graphics and Compute Technologies organization is responsible for capturing and analyzing advanced graphics, media, and compute use cases and executing them on models of future silicon. We are looking for exceptionally dedicated individuals who possess strong interest in the modeling, simulation and analysis of mobile, desktop and data center devices.

Minimum Qualifications

Technical BS/MS/PhD or equivalent degree in Computer Science, Computer Engineering, Electrical Engineering or related field. 3+ years of proven industry or research experience in building performance models of use cases running on CPUs, GPUs, NPUs or other hardware accelerators. Experience validating hardware and software against performance goals, using measured data from test systems. Strong software engineering skills and excellent proficiency in Python. Deep understanding of computer architecture, including processing units, interconnects, and memory hierarchies in modern SoCs, and the trade-offs between CPU, GPU, NPU, and other accelerator implementations. Strong ability to build abstract performance models of use cases and platforms from performance counters and other measurements, and to characterize their performance. Strong data reasoning skills, including the ability to design experiments, analyze data, and present results. Excellent communication and collaboration skills.

Preferred Qualifications

Hands-on experience in implementing one or more of: graphics and rendering pipelines, media pipelines, or games, and analyzing their performance characteristics. Working knowledge of system software, such as drivers, firmware, or frameworks, and how it affects performance. Experience in building simulation technologies. Experience collaborating in large cross-functional projects.

Description

Our team is seeking extraordinary performance modeling and analysis engineers with validation experience who are passionate about building accurate models that project the performance and power of future Apple Silicon platforms. You will model new and emerging use cases in graphics, games, media, and machine learning on devices that range from Apple Watch, iPhone, iPad, Apple Vision Pro and Mac to the data center. These models span software stacks, including drivers, firmware, and frameworks, alongside the hardware they run on. This is an opportunity to shape the architecture of future Apple Silicon and software, and influence the design of the next generation of hardware platforms.

Responsibilities

Build models of applications, platforms and software stacks, and the associated tools used to test the viability of future products and project their performance. Capture device traces, analyze them, and simulate them on hardware models. Profile use cases on current silicon and software to understand how they use the System-on-Chip (SoC). Validate them against performance goals. Correlate models against measurements on current silicon, and find and close sources of error. Collaborate with cross-functional teams including product, hardware architecture, software driver, firmware, frameworks and application teams, to define the vision and technical requirements for future products and present analysis results. Learn about the state of the art in graphics, media, games, machine learning, SoC architectures, and validation methodologies.