Fullstack engineer with AI experience building second brain to help Clinical Research Startup

We are looking for an experienced fullstack engineer with experience building an AI system or integrating one into a legacy project. We have too many clinical research papers that need to be in a protected environment and must be accessible via AI chat. It must be our second brain to help existing researchers. Key Responsibilities: AI/RAG: Implement a Retrieval-Augmented Generation (RAG) system using Amazon Bedrock or Azure OpenAI with high-accuracy. Security: Implement data masking, VPC isolation, and AWS Guardrails to protect our research paper. UI/UX: Develop a professional, full-screen dashboard (using Next.js or Streamlit) with data visualisation and an Audit/Admin Dashboard for human-in-the-loop review. Required Skills: Proven experience with LLM Orchestration (LangChain, LangGraph, or Bedrock AgentCore). Deep understanding of Vector Databases and semantic search. Strong background in Python/NodeJs and SaaS software development. Experience with Stripe API and AWS Cognito for SaaS billing and auth. Preferred: Experience in the Healthcare/Clinical research sector.