Applied Scientist, New Construction

Zillow Zillow · Consumer · United States · Remote

The Shopping AI team at Zillow is looking for an Applied Scientist to drive the next generation of ranking, recommendation, and generative AI systems for Zillow's home-shopping experience. This role involves researching, designing, and deploying innovative machine learning models, including LLM-based retrieval and RAG-style systems, to improve user discovery and interaction with homes. The scientist will lead the full model lifecycle from ideation to deployment and monitoring, collaborating with cross-functional teams and leveraging large-scale data systems.

What you'd actually do

  1. Research, design, and prototype new machine learning models for Zillow’s consumer products, including search, ranking, recommendations, and notifications.
  2. Lead the full model lifecycle: from ideation and offline experimentation on large datasets to online deployment, A/B testing, and ongoing performance monitoring.
  3. Develop and test novel modeling approaches, such as deep learning architectures and large language models (LLMs), to improve the home-shopping experience.
  4. Apply cutting-edge AI techniques, including LLM-based retrieval and RAG-style systems, to create more natural and conversational property search experiences.
  5. Optimize how and when homes are displayed to users, ensuring relevance and context in every interaction.

Skills

Required

  • Python
  • PyTorch
  • TensorFlow
  • CatBoost
  • scikit-learn
  • Hugging Face
  • Spark
  • Hive
  • Databricks
  • Airflow
  • hypothesis formation
  • experiment design
  • result analysis
  • clear communication to technical and non-technical partners
  • search/information retrieval
  • personalized ranking/recommender systems
  • generative AI/LLM-based systems
  • PhD or Master’s degree in a relevant field (Computer Science, AI, Data Science, or related), or equivalent industry experience

Nice to have

  • ownership
  • scientific rigor
  • growth mindset
  • curiosity and excitement for applying generative AI and LLMs

What the JD emphasized

  • solve real-world business problems, not just academic benchmarks
  • demonstrated experience in at least one of the following: search/information retrieval, personalized ranking/recommender systems, or generative AI/LLM-based systems

Other signals

  • ranking
  • recommendation
  • generative AI
  • LLMs
  • RAG