I am a PhD in Computer Science at the University of Maryland, Baltimore County, where my research focuses on large language models (LLMs), retrieval-augmented generation (RAG), and reasoning-aware evaluation systems. My work centers on building more robust, interpretable, and efficient AI pipelines that can power applications in scientific reasoning, healthcare, and decision-making. I have developed FilterRAG, a scalable framework for grounding and verifying LLM outputs, and FedMentalCare, a federated learning system for privacy-preserving behavioral signal analysis using LLMs. I am passionate about developing trustworthy and application-driven AI systems, particularly in healthcare and human-centered reasoning. I enjoy collaborative, cross-disciplinary research that bridges theory and real-world impact.