I built a RAG-based medical AI assistant using LLMs, embeddings, and vector search. I implemented document ingestion, retrieval pipelines, and backend APIs for conversational inference, using semantic retrieval and prompt engineering to improve response relevance and reduce hallucinations.
As a Python Full Stack Developer Intern at Wisdom Praise Infotech, I developed Django backend functionality, integrated REST APIs, and managed PostgreSQL databases. I also developed a road-monitoring backend with Java and Spring Boot, deploying it on AWS with Docker and Terraform.
