Experienced n8n Developer Needed

We are looking for an experienced n8n Developer to build an automated Document Ingestion & RAG (Retrieval-Augmented Generation) pipeline. The goal of this system is to automatically watch an enterprise storage folder (Google Drive/Dropbox), process unstructured PDF policy documents, chunk and embed the text into a Vector Database (Pinecone/Qdrant), and expose an AI query interface via Slack/Webhooks for internal team search. What You’ll Be Building: Automated Ingestion Workflow: Triggers on new/updated PDF uploads in Google Drive, extracts clean text, and splits content into semantic chunks (~500 tokens with overlap). Vector Embedding Engine: Connects n8n to an embedding model (OpenAI / Cohere / Hugging Face) to generate vector embeddings and upsert them into Pinecone with custom metadata filtering (e.g., doc_id, created_date, department). Conversational Query Pipeline: A secondary n8n workflow triggered via Slack Slash Command (/ask) or Webhook that queries Pinecone for context, feeds the top results into an LLM (Groq / Claude / GPT-4), and streams a accurate, cited answer back to the user. Error Handling & State Tracking: Robust error handling nodes to manage rate limits, parsing errors on corrupted PDFs, and failed API calls without breaking execution. Requirements: Proven experience building production n8n workflows using advanced HTTP Request nodes, Code nodes (JavaScript/Python), and native LangChain/AI nodes. Strong hands-on experience with Vector Databases (Pinecone, Qdrant, or Weaviate). Solid understanding of RAG architectures: semantic chunking, embedding generation, vector distance metrics, and prompt engineering. Experience integrating third-party APIs (Google Drive API, Slack API, OpenAI/Groq API). Ability to write clean, modular workflows with inline documentation and error-handling sub-workflows. Preferred / Nice-to-Have: Experience self-hosting n8n via Docker/VPS. Familiarity with local/open-source LLMs (Ollama) or high-speed inferencing providers (Groq). To Apply, Please Include: A brief summary of an n8n workflow or AI/RAG project you have shipped (a screenshot or short Loom video is ideal). Which vector database(s) you have integrated with n8n in past builds. Your hourly rate or estimated fixed price and timeline to deliver a working 2-workflow system.