•
Led the development and optimization of backend services using NestJS, integrating multiple Large Language Models (LLMs) tailored to specific use cases, achieving a 30% increase in processing speed and enhancing system scalability
•
Designed and deployed a Retrieval-Augmented Generation (RAG) chat system leveraging ElasticSearch and Python, improving document-based query accuracy by 25% and elevating user satisfaction through more precise responses
•
Directed a cross-functional team in creating an AI agent project that integrated LLMs with automated decision-making capabilities, reducing manual intervention by 40% and accelerating operational workflows
•
Established and enforced comprehensive unit testing protocols, increasing code coverage by 35%, significantly reducing production bugs, and mentoring junior developers on quality assurance best practices