You will own the deployment, reliability, and observability of the AI Agent Platform across Azure and AWS. This includes managing the Linux fleet, CI/CD pipelines, and the MLOps/LLMOps infrastructure to ensure safe and efficient model releases.
Act as the first point of contact for emergency building operation calls outside of business hours. Triage urgent issues, dispatch appropriate personnel, and maintain accurate records within the service management system.
Design and build AI agents on a LangGraph runtime, focusing on prompt engineering and the development of rigorous evaluation datasets. Implement applied machine learning models and RAG pipelines to improve agent intelligence and data-driven decision-making.
