I focus on harnessing the power of artificial intelligence and machine learning to solve complex operational challenges in post-exascale high-performance computing (HPC). By integrating advanced AI/ML techniques with HPC infrastructures—such as the Frontier exascale supercomputer—I develop data-driven solutions for operational analytics. This work includes leveraging large language models (LLMs) to automate everything from exploratory data analysis to predictive modeling, thereby lowering the barrier for HPC operators and system engineers to apply AI/ML effectively.

Beyond operational analytics, I explore new ways to combine HPC capabilities with modern deep learning frameworks** to improve supercomputer reliability, energy efficiency, and automate system management. My goal is to democratize AI/ML in HPC environments, ensuring that operational teams can benefit from cutting-edge AI research without requiring extensive machine learning expertise.