Python Backend Developer (RAG)

We are looking for a Python Backend Developer to build a custom Retrieval-Augmented Generation (RAG) chat application. Our goal is to build a lean, high-performance system from the ground up, focusing on custom logic for data retrieval and AI orchestration rather than relying on heavy third-party frameworks.

Key Responsibilities

• Custom RAG Development: Build the end-to-end RAG pipeline, including custom document parsing, text chunking strategies, and context injection logic.
• API Architecture: Develop and scale high-concurrency, asynchronous RESTful APIs using FastAPI (preferred) or Flask.
• Vector Search Implementation: Integrate and optimize vector databases (e.g., pgvector, Pinecone, or Weaviate) to ensure high-precision retrieval for AI grounding.
• Core AI Logic: Implement memory management, window handling, and custom prompt engineering natively in Python.
• System Performance: Optimize the latency of the Retrieve-the...