Description
We are seeking a skilled Python developer to build a Retrieval-Augmented Generation (RAG) demo using Python and FastAPI. The objective is to create a functional proof of concept that demonstrates how an LLM can retrieve relevant information from a knowledge base and generate accurate, context-aware responses. The ideal candidate should have hands-on experience with RAG architectures, vector databases, embeddings, and LLM integration. Experience with FastAPI is essential, while familiarity with Django, Scrapy, and modern AI frameworks is a strong advantage. Key Responsibilities: * Develop a RAG-based demo application using Python and FastAPI. * Integrate an LLM with a vector database and embedding model. * Build clean, well-structured REST APIs. * Write maintainable, well-documented, and scalable code. * Test and optimize the application for performance and reliability. Preferred Qualifications: * Strong proficiency in Python and FastAPI. * Experience with RAG frameworks such as LangChain or LlamaIndex. * Knowledge of vector databases (FAISS, ChromaDB, Pinecone, Weaviate, etc.). * Familiarity with OpenAI, Hugging Face, or similar LLM providers. * Experience with Django and Scrapy is a plus. * Good communication skills and the ability to work independently. If you have experience developing AI-powered applications and can deliver a high-quality RAG demo, we'd love to review your proposal. Please include relevant project examples, GitHub repositories, or portfolio links showcasi