About the Role We’re hiring a strong Python engineer to architect and ship scalable LLM systems — not prototypes, but reliable infrastructure. What You’ll Own Design and build end-to-end RAG systems Develop stateful, multi-step agent workflows Implement multi-source data ingestion (documents, APIs, email, cloud drives) Architect secure, multi-tenant AI infrastructure Improve retrieval accuracy, latency, and cost efficiency Build guardrails, structured outputs, and evaluation loops to reduce hallucinations Core Responsibilities Architect scalable LLM-powered backend systems Implement tool-calling and structured response pipelines Optimize prompt strategies and memory management Deploy and maintain cloud-native services Monitor performance, reliability, and cost usage Required Skills Strong Python (async programming, typing, clean architecture) Production experience with LLM APIs (OpenAI, Anthropic, Gemini, etc.) Deep understanding of RAG systems and retrieval optimization Experience with LangChain and/or LangGraph Experience building agent workflows beyond basic chatbots Hands-on experience with vector databases Understanding of token limits, context windows, and cost trade-offs Cloud deployment experience (AWS, GCP, or Azure) Tech Stack Python LLM APIs LangChain / LangGraph Vector database Redis / background workers AWS / GCP