Full Stack AI Engineer Needed for AI-Powered Document Processing Platform

We are looking for a Full Stack AI Engineer to build a working MVP of an AI-powered document processing and knowledge assistant. The goal is to allow users to upload business documents such as PDFs, DOCX files, and text files, process the content, store the relevant information, and ask questions through an AI-powered chat interface. Scope of Work The developer will be responsible for building the initial MVP, including: Backend API using Python, FastAPI or Django Document upload and processing pipeline Text extraction and chunking Embedding generation and vector storage using pgvector or Pinecone RAG-based question answering AI integration using OpenAI, Anthropic, or AWS Bedrock Basic conversational memory React-based frontend for document upload and chat PostgreSQL database integration Redis/Celery for background document processing where required Dockerized application setup AWS deployment using services such as EC2, S3 and RDS Basic logging, error handling, and monitoring GitHub repository with clear setup and deployment instructions Expected Workflow The final application should allow a user to: Upload one or more documents. Process and index the documents. Ask questions about the uploaded content. Receive AI-generated answers based on the documents. Maintain basic conversation context. View uploaded documents and processing status. Technical Requirements Strong experience with the following is preferred: Python • FastAPI/Django • React • PostgreSQL • Redis • RAG • LangChain/LangGraph • OpenAI/Anthropic/AWS Bedrock • pgvector • Docker • AWS • GitHub Actions The code should be structured for future expansion rather than being a quick prototype that needs to be rewritten later. Deliverables By the end of the 7-day period, we expect: Functional full-stack MVP Working document ingestion pipeline RAG-based AI assistant React frontend PostgreSQL/vector database integration Docker configuration Deployment on AWS GitHub repository Basic documentation One final testing and bug-fixing pass Timeline 7 days total Days 1–2: Backend architecture, database setup, authentication/basic project structure and document upload. Days 3–4: Document processing, embeddings, vector search and RAG pipeline. Day 5: AI chat functionality and frontend integration. Day 6: AWS deployment, Docker configuration and basic monitoring. Day 7: Testing, bug fixing, optimization and documentation. Budget $500 fixed price This project is intended as an MVP with a clearly defined scope. If the initial implementation goes well, there will be opportunities for additional work involving advanced AI agents, multi-user support, improved retrieval, analytics, integrations and production scaling. Who We're Looking For We're looking for someone who can handle the project end-to-end, rather than only implementing individual features. You should be comfortable making reasonable architectural decisions, debugging issues independently, and delivering a working application within the 7-day timeframe. Please include examples of AI/RAG applications or full-stack platforms you have previously built.