GPU Performance Engineer (Platform Architecture & Modeling)

Quick Facts

• Role: GPU Performance Engineer (Platform Architecture & Modeling)

• Focus: GPU simulation, performance modeling, and architectural tuning

Description

You will work with architecture, design, and software partners to define and tune Apple’s next-generation GPU architectures. The role centers on building and maintaining a high-performance C++ GPU model, coding/debugging performance and functional behavior, and adding modern features such as machine learning for AI, ray tracing, and mesh shading. You will ensure model accuracy through validation and correlation against RTL and other models, and analyze large datasets to assess feasibility and propose architectural changes.

Responsibilities

• Develop and maintain a high-performance C++ model of next-generation GPUs

• Code and debug performance and functional GPU models

• Implement modern GPU features (machine learning for AI, ray tracing, mesh shading, etc.)

• Validate model accuracy and correlate with other models and RTL

• Build and use tools to analyze large volumes of model-generated data

• Run performance experiments, analyze results, and propose architectural changes

Requirements

• Bachelor’s degree

• Experience writing and debugging C++ code

• Experience with scripting languages such as Python or Ruby

• Understanding of GPU/CPU architectures

• Troubleshooting and correlating performance issues across multiple models

Benefits

• Highly visible, cross-discipline role with critical impact on highly performant products

• Collaborative environment with experienced architects, modeling engineers, compiler engineers, and software teams