PhD Architecture Research Intern: GPU Systems

NVIDIA; Seattle (WA); On-site; USD 52,000 - 129,000; Full time

Benefits offered by this job

Intern benefits

Competitive hourly pay

Job summary

NVIDIA invites you to join our Architecture Research Group as an intern, contributing to the future of GPU and data-center computing. You’ll explore concepts across GPUs, memory systems, accelerators, and data-center platforms, shaping ideas from modeling to prototype tooling.

You’ll collaborate with researchers and product teams, tackle challenges in architecture, compilers, and runtimes, and help translate insights into NVIDIA products while gaining exposure to cutting-edge workloads in AI and

Qualifications

• Pursuing PhD in CS, CE, EE, Physics or Math.
• Experience in hardware/software/algorithm development in graphics or related fields.
• Strong programming in C/C++ and scripting languages.
• Experience as a CUDA programmer.
• Background building computer system simulators.
• Experience building low-level software such as runtime systems, binary translators, or compilers.
• Strong background in computer architecture and parallel architectures.

Responsibilities

• Investigate new architecture concepts for GPUs, memory systems, accelerators, and data-center-scale platforms.
• Study emerging workloads and 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 ideas.
• Research memory hierarchy, coherence, consistency, data movement, and system-level programmability.
• Collaborate with NVIDIA researchers, GPU architects, software teams, and product groups to evaluate concepts.
• Communicate research findings through presentations, reports, and potential publications.
• Help transfer successful research ideas into NVIDIA product teams.

Skills

C/C++ programming

scripting languages

CUDA programming

parallel computing

architectural knowledge

Education

Pursuing PhD in CS/CE/EE/Physics/Math

Tools

CUDA toolkit

CPU/GPU programming environments

workload simulators

Job description

NVIDIA invites you to join our Architecture Research Group as an intern, contributing to the future of GPU and data-center computing. You’ll explore concepts across GPUs, memory systems, accelerators, and data-center platforms, shaping ideas from modeling to prototype tooling.

You’ll collaborate with researchers and product teams, tackle challenges in architecture, compilers, and runtimes, and help translate insights into NVIDIA products while gaining exposure to cutting-edge workloads in AI and