What we need to see: 

• Must be actively enrolled in a university pursuing a Ph.D. degree in Computer Science, Electrical Engineering, or a related field, for the full duration of the internship; anticipated graduation date (month and year) must be clearly indicated on a resume or CV to be considered.  

• Depending on the internship, prior experience or knowledge requirements could include the following programming skills and technologies: C, C++, Python, CUDA 

• Strong background in research with publications at top conferences. 

• Excellent communication and collaboration skills. 

Potential internships require research experience in at least one of the following areas: 

• Chip-level and System-level Architecture 

GPU and Multi-GPU Architecture Scalable memory systems and new memory technologies 

Scalable on-chip and off-chip interconnects 

Chip-level and system-level scheduling 

Power, performance, and energy-efficiency in large-scale systems 

Specialized accelerators for workloads like AI algorithms, crypto algorithms, databases, etc. 

Hardware-software co-design 

• Systems for AI/ML 

Systems Infrastructure for large LLM training and inference 

Systems/AI algorithms codesign (e.g., for sparsity) \

AI/ML for systems (hardware design, code optimization, etc.) 

ML for EDA 

• Programming Systems 

GPU-accelerated algorithms 

Languages and programming models for parallel computing 

Optimizing compilers and AI-based performance assistants 

Distributed runtime systems 

Systems software and operating system interfaces 

Optimizing GPU-accelerated workloads 

Compilers and code verification 

• High-Performance Networking and Interconnects 

Large-scale GPU networking 

Topologies, routing, and congestion control 

Networking techniques at the intersection of scale-out and scale-up 

• VLSI and Electronic Design Automation (EDA) 

GPU Accelerated EDA