Build robust self-service tooling and automated evaluation frameworks, utilizing Large Language Model (LLM) simulators and judges to continuously monitor performance, manage quality hill-climbing, and prevent regressions. Architect and refine unified, scalable APIs for critical functions like catalog ingestion (e.g. Universal Commerce Protocol), real-time agent configuration, and "one-line SDK" site integration. Design infrastructure that shrinks the onboarding gap, enabling rapid deployment for a global customer base ranging from large enterprises to Shopify merchants.
Drive the feature life-cycle from experimentation to production, ensuring high reliability for complex shopping journeys that combine search, sales, and support.
Job description provided by Google.
View the original posting
