● Built and integrated Generative AI applications using Python, LangChain, Google Gemini API, and Groq, with a focus on prompt engineering and context-aware response generation. ● Designed and refined prompts for LLM applications, including role-based prompting, few-shot prompting, and conversational workflows to improve response quality and relevance. ● Developed RAG-based applications using ChromaDB and Hugging Face embeddings for document retrieval and context-grounded LLM responses. ● Implemented multi-turn conversational workflows and session-based memory for maintaining relevant conversation context. ● Built and tested AI application workflows using LangChain and LangGraph, including agent-based architectures and tool-calling capabilities. ● Integrated LLM applications with APIs and backend services using FastAPI, and developed interactive prototypes using Streamlit. ● Deployed AI applications using AWS EC2, AWS S3, and Hugging Face Spaces, gaining hands-on experience with AI application deployment. ● Analyzed and debugged AI-generated responses, iterating on prompts and application logic to improve response accuracy and reliability.