Build and improve production LLM agents and AI features through evaluation, experimentation, observability, prompting, context engineering, tool use, and workflow design. Develop backend services, APIs, data models, and feedback pipelines that make agent behavior reliable and measurable. Investigate performance issues, run staged rollouts and production replays, define quality standards, and partner with Product, Data Science, and Sales to deliver business outcomes with appropriate privacy, security, and human-oversight safeguards.