AI/ML Engineer Needed for Production RAG Chatbot and Workflow Automation System

We are looking for an experienced AI/ML Engineer to help us build a production- ready AI assistant for our customer support and internal operations team. We have a growing knowledge base made up of support tickets, PDFs, SOPs, website content, customer documents, and internal training material. We want to build an AI assistant that can answer questions accurately, provide source references, summarize customer issues, and help our team reduce manual work. This is not a simple ChatGPT wrapper. We need someone who has real experience building AI chatbots, RAG pipelines, LangChain workflows, vector search, API integrations, and production AI systems. What we need:  Build a custom AI chatbot using LLMs and RAG  Connect the chatbot with documents, PDFs, website content, and internal knowledge base  Implement vector search using Pinecone, Chroma, FAISS, pgvector, or similar  Add source citations and confidence handling for answers  Build backend APIs using Python, FastAPI, or Django  Create workflows for ticket summarization, document Q&A, and customer routing  Add prompt templates, fallback logic, guardrails, and conversation history  Deploy the system on AWS, Azure, or GCP  Set up logging, monitoring, and basic performance tracking  Optionally build a simple admin dashboard for uploads and knowledge base management Required skills:  Python  FastAPI or Django  LangChain or LlamaIndex  OpenAI API, Claude, Gemini, or similar LLMs  RAG and vector databases  NLP and document processing  API integration  Cloud deployment  Production AI system experience Nice to have:  Experience with customer support automation  Experience with insurance, healthcare, SaaS, or contact center workflows  Experience building AI agents or automated business workflows  Experience with speech recognition, recommendation systems, or ML pipelines Ideal freelancer: We want someone who can think beyond the model and help us design the full system properly. You should be able to explain the architecture, identify risks early, communicate clearly, and provide regular updates. Please include: 1. Examples of AI chatbots, RAG systems, or LangChain projects you have built 2. Your suggested architecture for this project 3. Which vector database and LLM stack you recommend 4. Estimated timeline for an MVP 5. Any risks we should consider before development I try to read every proposal and will choose the best.