• Own the intelligence behind our Ads agents. • Design the Ads semantic/context layer and build vertical AI agents that analyze campaigns, diagnose performance, and recommend actions that improve ROAS, pacing, and partner outcomes. • Partner with Ads GTM, Product, Data Science, and Engineering to ship production agents with measurable lift. • Define Ads ontologies and metrics for campaigns, budgets, bids, creatives, audiences, and placements. • Build dbt models and curated marts in Snowflake with clear data contracts, tests, and SLOs. • Ingest and enrich unstructured Ads content and publish retrieval-ready datasets using managed search/vector services. • Design and evaluate retrieval workflows (RAG) with existing services for hybrid search and re-ranking; set quality/latency targets and iterate via experiments. • Design agent reasoning and policies on ads, including tool definitions and human-in-the-loop approvals. • Establish evaluation suites covering precision/recall, calibration, hallucination rate, latency, and cost. • Run A/B or uplift experiments to quantify impact and guide iteration. • Translate Ads problems into agent behaviors and own KPIs such as ROAS lift, pacing accuracy, RCA precision/recall, forecast MAPE, and time-to-insight.