My research focuses on the intersection of Agentic AI, Generative Models, Applied Machine Learning, and Bioinformatics, addressing both fundamental computational challenges and real-world industry applications. On the bioinformatics side, my work explores machine learning-based approaches for predicting protein post-translational modification sites, including glutarylation, malonylation, methylation, and propionylation, leveraging evolutionary and structural features to improve prediction accuracy. More recently, my research has expanded towards LLM-powered systems, incorporating techniques such as Chain-of-Thought reasoning, LangGraph, and domain adaptation to build intelligent assistants for enterprise and digital banking environments. These efforts aim to enhance the generalizability, interpretability, and practical deployability of AI-driven solutions across scientific and industry settings.