Research

My research is at the intersection of software engineering and artificial intelligence. My work addresses the test and evaluation challenges in AI-enabled software systems by adapting established software testing principles and developing novel methodologies to evaluate unique characteristics of AI-enabled software systems. My work spans test and evaluation of machine learning algorithms, deep neural network models, and large language models, creating test methods and frameworks that address the challenges each technology presents. Through my research, I contribute to the development of methods, frameworks, and metrics for systematic assessment of AI-enabled software systems, enabling reliable and trustworthy AI deployment across diverse applications. Additionally, I am exploring how AI techniques can enhance traditional software testing practices, particularly through LLM-augmented test generation.