Looking for Senior AI Architect (Python, LangChain, Custom APIs)

We are a fast-growing AI Automation Agency looking for a Senior AI Architect to design, build, and deploy production-grade AI systems for our enterprise and mid-market business clients. This is a contract position with the potential for long-term retainer work. You will not be building basic wrapper apps. You will be responsible for mapping out and executing complex multi-agent architectures, robust Retrieval-Augmented Generation (RAG) pipelines, and deep custom API integrations into proprietary business software. Core Responsibilities Design secure, scalable backend architectures capable of handling high-throughput data processing and multi-step AI reasoning. Develop custom APIs and microservices using FastAPI or Flask to seamlessly connect LLMs with client CRMs, databases, and internal tools. Implement advanced RAG pipelines, managing data ingestion, embedding generation, and vector database retrieval. Optimize system performance, focusing heavily on API latency, token management, cost controls, and robust error handling/fallback mechanisms. Technical Requirements Language: Expert-level Python developer with a deep understanding of asynchronous programming. Frameworks: Extensive, hands-on experience with LangChain, LangGraph, or LlamaIndex for orchestration. Vector Databases: Production experience with Pinecone, Weaviate, Qdrant, or Milvus. APIs & Deployment: Mastery of RESTful API design, OAuth authentication protocols, and cloud infrastructure (AWS or GCP). How to Apply To be considered, you must submit your application with: A brief breakdown or Loom video walkthrough of a production-ready AI system you engineered from scratch. A link to your GitHub profile or relevant repository showcasing your clean, modular Python code.