Contributing to real-time AI/ML and Generative AI projects by designing end-to-end systems, including data curation, preprocessing, model training, fine-tuning, and deployment. Building LLM-powered multi-agent and RAG pipelines using LangChain and vector databases for intelligent applications. Deploying scalable AI solutions via Django REST APIs and AWS with performance optimization. Additionally, delivering technical training in AI/ML and supporting institutional initiatives through academic and technology-driven programs.