PhD Research Intern, Architecture – 2027

About the role

The NVIDIA Architecture Research Group is seeking an intern to help define the future of GPU and data‑center computing. The research spans GPU microarchitecture, memory systems, large‑scale data‑center hardware, emerging accelerators, and the architectural implications of new AI, scientific computing, robotics, and other workloads. Interns will apply knowledge of computer architecture, parallel computing, compilers, runtime systems, and workloads to explore hardware and hardware‑software co‑design opportunities, working with researchers and product architects to formulate questions, develop concepts, and build models, simulators, prototypes, and experimental infrastructure.

Responsibilities

• Investigate new architecture concepts for future GPUs, memory systems, accelerators, and data‑center‑scale platforms.
• Study emerging workloads to identify architectural bottlenecks and opportunities.
• Explore hardware‑software co‑design across architecture, compilers, runtime systems, programming models, and applications.
• Develop models, simulators, prototypes, and experimental tools to evaluate new architecture ideas.
• Research new approaches to memory hierarchy, coherence, consistency, data movement, and system‑level programmability.
• Collaborate with NVIDIA researchers, GPU architects, software teams, and product groups to develop and evaluate promising concepts.
• Clearly communicate research findings through presentations, technical reports, and potentially research publications.
• Help transfer successful research ideas, methodologies, and tools into NVIDIA product teams.

Requirements

• Pursuing a PhD in Computer Science, Computer Engineering, Electrical Engineering, Physics, Mathematics, or a related discipline.
• Relevant industrial or university experience in hardware, software, or algorithm development for graphics, digital video, image processing, video games, consoles, mobile devices, consumer electronics, rendering software, or high‑performance computing.
• Strong programming ability in C/C++ and scripting languages.
• Experience as a CUDA programmer.
• Background in building computer system simulators.
• Experience building efficient low‑level software tools such as runtime systems, binary translators, or compilers.
• Strong background in computer architecture and parallel computer architectures.

Preferred qualifications

• Prior research experience and/or research publications at conferences such as ISCA, MICRO, ASPLOS, HPCA, or MLSYS.
• Versatility in using generative AI coding tools.
• Versatility in using GPU profiling tools and running deep‑learning models on GPUs.

Benefits

• Eligibility for NVIDIA intern benefits.

Pay

Hourly rate for interns ranges from $38 to $94, based on position, location, year in school, degree, and experience.

Applications will be accepted until September 21, 2026.