Spearheaded the development of a hybrid Artificial Intelligence and Large Language Model (LLM) system for querying biomedical databases and APIs, enhancing user interactions and streamlining data retrieval processes through natural language interfaces.• Ensured high accuracy and relevance of system responses to user queries by leveraging advanced techniques such as Natural Language Query Processing (NLQP) and Retrieval Augmentation Generation (RAG).• Proposed self-learning mechanisms within the system to continually improve performance over time, utilizing solved test case scenarios and analyzing correct and incorrect responses.• Directed a multidisciplinary team to investigate language learning models and AI applications in biomedical data retrieval, crafting a comprehensive solution that addressed diverse user needs; delivered a solution that led to a 15% increase in user satisfaction and a 25% reduction in data processing time.• Analyzed industry-specific data retrieval challenges in the biomedical sector, driving the creation of a user-friendly platform for scientific research; increased data retrieval efficiency by 50% and enabled broader access to vital information for researchers.• Generated performance metrics including Faithfulness, Answer Relevancy, Contextual Precision, Contextual Recall, and Contextual Relevancy to evaluate the effectiveness of the developed system in retrieving and generating biomedical data.

Worked on integrating Machine Learning and Full stack where we created a homepage on showcasing various crop types and its prices in future based on parameters such as yield in a particular month