GPU Internships - Architecture Validation, Performance Modelling & Platform Architecture

We will be hiring for the below internships in 2026/27 and across the available start dates: Autumn / Winter 2026 or Spring / Summer 2027.

Architecture Validation: Building experience interpreting hardware functional specifications together with architects, micro-architects, and designers, you will be able to build bit-accurate C/C++ models of the GPU or design workloads to verify new GPU features through models. You will partner with our verification and software teams to identify bugs in the workloads, model and hardware, collaborate to verify architectural solutions, and communicate recommendations to the wider team.

Performance Modelling: You will have impact in defining and optimising Apple's GPU micro-architecture. Through collaboration, you will seek out areas for GPU performance improvement while collecting data and measurements that either confirm new features or rule them out. You will work with experienced designers in micro-architecture and RTL to assess the feasibility of ideas, refine them and create new ones. The role requires the analysis of interesting workloads across existing and new product categories to identify bottlenecks and opportunities for improvement. You will be architecting new simulator features and brainstorming novel ideas to boost simulation performance. We also cross-collaborate as a larger performance team to maintain and improve the simulation environment and look for ways to boost the productivity of the entire team.

Platform Architecture: Are you ready to be at the forefront of architecting the next generation of Apple GPUs? This role will require you to analyze the performance of existing and future looking workloads and propose, alongside with world-class GPU and SoC Architects, new features and research on novel ideas to boost to new heights the performance of our GPUs. To do so, you’ll use performance and energy models to evaluate, iterate and tune the different ideas until the proposal is mature enough to be presented to senior GPU Architects to make a decision on its feasibility. You’ll also cross-collaborate as a larger architecture and performance team to maintain and improve the simulation environment and look for ways to boost the productivity of the entire team.