The opportunity
Airbnb was born in 2007 when two hosts welcomed three guests to their San Francisco home, and has since grown to over 5 million hosts who have welcomed over 2 billion guest arrivals in almost every country across the globe. Every day, hosts offer unique stays and experiences…
What you'll do
Build agentic analytics pipelines that automate insight generation across all: key metrics including contact volume, handle time, and resolution quality — reducing analytical drag across CS.
Develop reusable skill libraries: composable agent tools (volume lookups, NPS pulls, handle time calculations) callable across workflows and teams.
Design and govern prompt templates and playbooks: standardised, governed prompts for recurring analytical questions (e.g. “what drove contact volume this week”).
Build orchestration workflows: multi-step pipelines that chain skills together to produce automated insight narratives and proactive alerts without manual intervention.
Deploy self-serve interfaces that enable non-technical personas to query certified data independently.
Ship rapid, prompt-driven dashboards that compress the cycle from business: question to live view, serving varied personas without analyst bottleneck.
What they're looking for
- Automate business reviews: scheduled, agent-generated summaries of key CS metrics delivered to stakeholders without manual effort.
- Build and maintain evaluation and observability frameworks that monitor agent: output quality, detect drift, and ensure outputs stay within governed data boundaries.
- Define, document, and certify metrics within Minerva 2.0 and Midas, ensuring: agentic outputs and self-serve interfaces are anchored to a single source of truth across CS.
- Drive the analytics roadmap, prioritization, and delivery of solutions in up: to a quarter ahead. Execute projects with regular direction providing constant updates to business stakeholders, analytics management and deliver against agreed timelines.