• Lead early-phase AI systems: Design and build AI-first user experiences from the ground up, pairing rapid experimentation with strong measurement loops to evaluate performance, relevance, safety, and cost in production. • Influence product direction: Bring an engineering-driven perspective to what we build, how we build it, and which tradeoffs are worth making at early stages—charting a multi-step path that turns quick wins into durable, scalable capabilities. • Design and build scalable AI systems: Once direction is validated, evolve prototypes into reliable, maintainable, and observable production systems, balancing iteration speed with long-term platform health. • Build AI-powered product experiences: Develop AI-assisted modeling and authoring workflows to accelerate plan design, data mapping, and explanation for customers. • Deliver retrieval-augmented insights: Implement contextual help, explainers, and policy Q&A grounded in customer data and system metadata using robust retrieval-augmented generation patterns. • Own guardrails and evaluation: Design and implement evaluation and safety primitives—including offline and online evals, telemetry, human-in-the-loop workflows, safety filters, and red-teaming—to ensure trustworthy AI behavior. • Create reusable AI platform components: Build shared infrastructure for prompt orchestration, hybrid retrieval, caching, tracing, evaluation, and cost/performance controls that enable teams to ship AI features safely and efficiently. • Raise the technical bar: Contribute to architecture, coding standards, testing strategy, and mentoring; promote best practices across AI systems, platform design, and production readiness.