PhD Research Intern, System Software and I/O Architecture - Fall 2026

NVIDIA is seeking a PhD Research Intern with a focus in System Software and System I/O Architecture to contribute to the development of future fast, scalable storage accesses by GPU threads.

The intern will:

• Develop novel architectures and system software implementations to enable scalable multi-GPU platforms.
• Understand and analyze the interplay between application, operating systems, CPU and GPU architectures, and efficient algorithm designs.
• Collaborate with a diverse set of teams across the company, spanning software research, hardware engineering, and product groups.
• Publish original research and speak at conferences and events.

Requirements:

• Currently pursuing a Ph.D. in CE/CS/EE or similar program area.
• Research experience in computer architecture, operating systems, system administration, compilers, and/or HPC.
• Research experience designing and optimizing accelerated computing applications, with expertise in areas such as LLM inference, GPU-native database engines, and vector similarity search algorithms.
• Demonstrated expertise in one specific area of the above topics with the ability to become the go-to resource within a team from differing backgrounds.
• Experience with experimental computer architecture research, software infrastructure development and evaluation.
• A track record of well-documented open-source software release.
• Ability to work with emerging workloads such as recommender systems, graph analytics, and data frames.

Preferred qualifications:

• Experience with C, C++, CUDA, Python, Rust, and scripting languages. MPI and NCCL would be a plus.
• Strong interpersonal skills and being a creative and dynamic presenter is a huge advantage.
• A strong publication, patent, presentation, and research collaboration history is highly valuable.

The hourly rate for this internship is $30 - $94 USD.