About the role#
NVIDIA is seeking a PhD Research Intern to focus on System Software and I/O Architecture for the Fall 2026 term. This role contributes to the development of fast, scalable storage access for GPU threads, requiring co-optimization of architecture, runtime systems, operating systems, and compilers to improve throughput and energy efficiency.
What you'll do#
- Develop novel architectures and system software implementations for scalable multi-GPU platforms.
- Analyze the interplay between applications, operating systems, and CPU/GPU architectures.
- Collaborate with cross-functional teams across software research, hardware engineering, and product groups.
- Publish original research and present findings at conferences and events.
What you'll need#
- Current enrollment in a Ph.D. program in Computer Engineering, Computer Science, Electrical Engineering, or a related field.
- Research experience in computer architecture, operating systems, system administration, compilers, or high-performance computing (HPC).
- Experience designing and optimizing accelerated computing applications, including areas like LLM inference, GPU-native database engines, or vector similarity search algorithms.
- Proficiency in experimental computer architecture research and software infrastructure development.
- A track record of well-documented open-source software releases.
- Experience working with emerging workloads such as recommender systems, graph analytics, and data frames.
Location & details#
- Locations: Santa Clara, CA; Champaign, IL; or remote.
- Term: Fall 2026.
- Status: Full-time, paid internship.
- Compensation: Hourly rate between 30 USD and 94 USD, depending on location, degree, and experience.
- Eligibility: Applicants must be authorized to work without sponsorship.
