Hi there! 👋
I'm Sudharshan Balaji, a Ph.D. researcher at University of South Florida working in the SPRAI Lab. I focus on making AI systems less mysterious and more secure, combining large language models, federated learning, and medical NLP — while trying not to break production (too often).
My name is Sudharshan Balaji, and I'm a Ph.D. researcher at the University of South Florida, advised by Dr. Ning Wang in the Security and Privacy Research of AI Systems (SPRAI) Lab.
I build machine learning systems that are intelligent, interpretable, and resilient — often working at the intersection of AI security, federated learning, and natural language processing. My recent projects include building transformer-based intrusion detection systems, building medical AI systems, and studying how LLMs behave.
I completed my Master's degree at University of South Florida as well (yes, I liked it enough to stay), where I TA'd for some coding-heavy courses, survived thesis writing, and discovered the joy of debugging Flask apps at midnight.
Outside research, I enjoy playing video games, watching football (european one) and F1, trying to finish my side projects, and making academic learning fun (or at least meme-able).