At VE3 Global, I design and deploy Flask services for enterprise RAG applications, connecting knowledge retrieval to operational workflows. I built LangChain and LangGraph agent workflows that use tools to retrieve information and execute tasks across enterprise systems.
I’ve also developed document ingestion and extraction pipelines, semantic search with Milvus and Neo4j, and a FastAPI FAQ chatbot with intent classification and fallback routing. Earlier, as a Python Developer Intern at Neurealm(formerly GS Lab|GAVS), I worked on Django APIs, LLM and deep-learning tasks, and a cloud service comparison tool.
