I'm looking for a developer to build a project that implements a Retrieval-Augmented Generation (RAG) pipeline enabling semantic search and conversational AI with a resume (CV). The goal is to create a cost-effective architecture that runs the application logic locally while offloading heavy LLM inference to the cloud. The application should support semantic search over the resume and allow a conversational interface to answer questions about the resume content. This project is focused on building the RAG pipeline, integrating the embeddings, and ensuring a secure connection between the local backend and cloud model server. - Responsibilities Design and implement the RAG pipeline for resume semantic search Integrate embedding generation using HuggingFace models Set up local backend using FastAPI Connect to cloud LLM inference (Ollama) for conversation Implement secure tunnel using ngrok Debug and optimize the workflow Document setup and usage Project Details New project build (not an existing application) Focus on RAG architecture and secure local-cloud integration No major UI or frontend work required Requirements Experience with FastAPI and Python Strong understanding of RAG and semantic search Experience with LangChain or similar frameworks Familiarity with HuggingFace embeddings Ability to configure ngrok and secure local endpoints Clear communication and independent problem solving If you’re excited about building cost-effective AI systems and RAG pipelines, I’d love to hear from you.