Act like an owner ask questions, propose solutions, build consensus, and drive execution from concept to delivery. Build agent capabilities design and implement skills, plugins and typed tools for LLM agents that search, read, reason over and cite large private corporate. Make outputs verifiable build grounding and citation checks, access-aware retrieval, and automated review of agent-authored knowledge, so every result can be audited back to its sources.
Lead evaluation build evaluation suites and datasets with subject matter experts, measure factual accuracy, citation fidelity and multi-step reasoning, and use the results to drive improvements. Ship to production strong code quality, testing, CI/CD and monitoring for agent systems used daily by professionals.
Job description provided by Google.
View the original posting
