Senior Applied Scientist, Agentic AI

Zillow Zillow · Consumer · United States · Remote

Senior Applied Scientist on the Agentic AI team at Zillow, focusing on researching and developing advanced LLM-powered reasoning systems for real estate. The role involves prototyping, evaluating, and deploying agents capable of deep, multi-step reasoning, accurate tool use, and contextual decision-making, with a focus on improving reliability and quality through evaluation frameworks and post-training techniques.

What you'd actually do

  1. Design, prototype, and build advanced agentic systems capable of highly autonomous, context-aware, and adaptive interactions across diverse real estate use cases
  2. Apply test-time scaling and post-training techniques to develop agents that can reason, collaborate, compete, or negotiate in dynamic, goal-driven environments to fulfill user needs.
  3. Define and refine evaluation and experimentation processes for LLM-driven applications.
  4. Stay at the forefront of agentic AI research and innovation, bringing emerging techniques into practical application to shape product direction.
  5. Contribute to the broader scientific community through publications, conference presentations, and internal knowledge sharing

Skills

Required

  • LLM reasoning
  • Agentic systems
  • Machine Learning
  • NLP
  • multi-agent collaboration
  • multi-step reasoning
  • context-rich decision-making
  • experimental design
  • evaluation
  • qualitative and quantitative analysis
  • measurement of reasoning quality, generalization, and safety
  • publishing research

Nice to have

  • real estate domain expertise

What the JD emphasized

  • advanced LLM-powered reasoning systems
  • deep, multi-step reasoning
  • rigorous evaluation frameworks
  • agentic AI research and innovation
  • Ph.D. or equivalent experience
  • building large-scale, high-impact ML solutions
  • LLM reasoning models or AI agents capable of multi-step reasoning
  • rigorous experimental design and evaluation
  • Track record of publishing high-impact research

Other signals

  • LLM-powered guidance
  • AI agents
  • multi-step reasoning
  • tool use
  • production-grade AI systems