Senior Backend / Data Engineer for Enterprise GenAI (RAG) Project

About the Project: We are building a Proof of Concept (PoC) for an advanced AI knowledge retrieval system for a large enterprise client. The system will allow employees to query complex, unstructured documents in natural language, entirely within a closed and highly secure cloud environment. The project is led and technologically orchestrated by an AI strategy and product management agency, meaning the architecture, data flows, and PoC scope are already strictly defined. Your primary objective will be to develop the end-to-end data ingestion pipeline—from data extraction and custom parsing logic, to vector database indexing and LLM retrieval. Core Requirements: * Proven experience in Backend development and building Microservices (Strong preference for Python, but Node.js is also acceptable). * Data Engineering & Parsing: Proven ability to write custom code to extract, clean, and structure text from unstructured or semi-structured files (complex multi-row Excel sheets, PDFs, Word documents). * Deep, hands-on understanding of RAG (Retrieval-Augmented Generation) architectures, including advanced chunking strategies, working with Embeddings, and integrating LLMs (OpenAI / Azure OpenAI). * Experience with Vector Databases, with an emphasis on defining indexes and metadata filtering. Specific experience with Azure AI Search is a significant advantage. * Hands-on experience within the Azure cloud ecosystem, including deploying code to Azure App Service. * Experience integrating with secure enterprise APIs (such as Microsoft Graph API) to extract data from SharePoint environments. * Ability to work completely independently on the development side, fully "hands-on," with a drive to deliver rapid results in a PoC environment.