Build and operate applied AI systems, including LLM integrations, agentic workflows, data pipelines, evaluation frameworks, MCP tools, APIs, and governed content-serving layers. The role emphasizes production reliability, provenance, security, cost and latency management, regression detection, and human-reviewed AI outputs. Responsibilities include cloud deployment, structured content modeling, telemetry, governance, mentoring, and collaboration on AI standards. Strong Python, TypeScript, AWS, API, data pipeline, and production LLM experience are required.

Build and operate production applied AI systems, including LLM integrations, agentic workflows, data pipelines, evaluation frameworks, APIs, MCP tools, and governed content-serving layers. Develop reliable extraction and classification agents, model evaluation harnesses, telemetry, and structured data pipelines. Ensure security, privacy, provenance, reliability, latency, and cost controls while mentoring engineers and contributing to AI governance and standards.