Research Intern - AI Systems & Architecture
Core
Investigate emerging AI system architectures and analyze hardware, software, and model behavior interactions across large-scale inference workloads.
Role type
Research Intern (AI Systems & Architecture)
Builds
Analytical or simulation-based performance models, prototypes of new inference mechanisms
Domain
AI Systems, Computer Architecture, Large-scale Inference
Deliverable
research
Required skills
Performance modeling, Distributed systems, Hardware-software co-design, Python, C/C++, Deep learning frameworks (PyTorch), Original research direction definition
Preferred skills
CUDA, Triton, Performance-simulation tools, Large-scale system design, Accelerator/memory-system design principles
Technologies
PyTorch, CUDA, Triton
Responsibilities
Develop and evaluate performance models to identify bottlenecks, prototype new inference mechanisms, conduct experiments, synthesize research findings, communicate results to mentors
Seniority
Intern
