GPU Architect Intern - Summer 2026
Skip the busywork
ApplyBolt rewrites your resume for this exact role and hits submit. You just pick the jobs.
About this role
The NVIDIA GPU Architecture group is looking for creative architects to join and support various architecture efforts with a rewarding internship experience. A key part of NVIDIA's strength is to innovate in the graphics and parallel computing fields, delivering the highest performance in the world for graphics processing. This internship is crafted for individuals who desire an experience to improve our GPU architecture, develop new programming models, new architectures, and new infrastructure that is required to make this successful.
What you'll be doing:
In this position, you will be responsible for developing and improving various features in the GPU architecture that advance the state of the art in graphics features, performance, and efficiency. You would interact with other world-class architects and researchers to build simulators and infrastructure to design and validate these new features. Specifically, you will:
- Design and build new hardware features for future graphics architectures as well as create and elevate graphics algorithms.
- Invent and develop software for various hardware simulators and test infrastructures.
- Work in a dynamic team to document, design, develop tools to analyze and simulate, validate, and verify functional or performance models.
- Develop tests, test plans, and testing infrastructure for new graphics architectures.
What we need to see:
- Pursuing a Bachelor's or Master's degree in (CS, EE, Math).
- Strong programming ability: C / C++.
- Knowledge and background in computer architecture, graphics algorithms, and fundamentals of machine learning.
- Strong software/coding and debugging skills, and a balance of research and execution
- Relevant domains include; Graphics / Computer Architecture, Computer Vision, Spatial Intelligence, VR, and AI/ML
Ways to stand out from the crowd:
- Performance optimization and understanding of power architecture and efficiency is strongly preferred.
- Knowledge and background in Direct X and CUDA is a plus.