About the teamThe Agentic Foundations team is a focused group of 15-20 applied scientists within Zillow's broader Agentic AI organization, building the foundational AI technologies that power the next generation of home shopping experiences. This Senior Applied Scientist will focus on model post-training and reward modeling - the science that lets our agents measurably improve over time as part of a self-evolving agentic system. The role will drive complex, ambiguous work end-to-end, partnering closely with product, engineering, science, platform, and data teams to translate the latest advances in LLMs, reinforcement learning, and post-training into production impact. This is an exciting time to join as Zillow is building agentic skills across the full home-shopping journey - from search and personalized guidance to offer strategy and financing - at a scale of hundreds of millions of requests per day.

About the roleRole and responsibilities:

Own LLM post-training pipelines - SFT, DPO, and reinforcement fine-tuning (RFT/GRPO) - running training end-to-end on GPU infrastructure.

Build and train fast, multi-category reward models (PRMs) that emit scalar signals from contrastive preference pairs.

Design on-policy and online assessment: score live agent trajectories using LLM-as-a-Judge frameworks.

Translate offline evaluation rubrics into generalizable reward functions that work on arbitrary production traces.

Independently drive complex work end-to-end by collaborating across partner teams.

Provide technical leadership and mentorship while helping translate state-of-the-art AI research into production impact.

This role has been categorized as a Remote position. \