Principal Applied Scientist, Agentic AI

About the teamThe Agentic AI team at Zillow is transforming the real estate industry by helping millions of people navigate one of the most important decisions of their lives with AI-powered guidance. Our mission is to redefine the home shopping and transaction experience through an always-on assistant that combines deep real estate expertise, grounded data access, advanced reasoning, and the ability to take meaningful action on behalf of customers.Within the Agentic AI organization, the Applied Reasoning team builds the foundation for agents that perform complex, multi-step reasoning and for proactive, long-running agents that can anticipate customer needs and complete valuable work over time. We focus on advancing agent depth, breadth, proactiveness, and reliability through rigorous experimentation, evaluation, and production innovationAbout the roleAs a Principal Applied Scientist, you will set the science direction for advanced reasoning and long-running agent systems within the Agentic AI organization. You will partner closely with applied scientists, machine learning engineers, software engineers, product leaders, and senior stakeholders to define the science roadmap for Zillow's agentic experiences. This is a high-impact principal individual contributor role responsible for translating emerging advances in agentic AI into reliable, differentiated customer experiences.You will get toDefine and drive the end-to-end applied science strategy for advanced reasoning and long-running agent systems, balancing innovation, customer value, reliability, safety, and business priorities.Advance agent capabilities through agent architecture and harness design, context and memory engineering, test time scaling, post-training, evaluation and data flywheel.Establish rigorous evaluation frameworks for agentic systems, including task- and trajectory-level evaluation, long-horizon benchmarks, controlled experiments, ablation studies, and online measurement.Influence senior and ex