AirflowPythonPyTorchScikit-LearnSparkTensorflowAIMachine LearningMLDeep LearningGenerative AILLMLarge Language ModelsTensorFlowscikit-learnHugging FaceCatBoostData EngineeringDatabricksA/B TestingCommunication
About this role
Role Overview
Research, design, and prototype new machine learning models for Zillow’s consumer products, including search, ranking, recommendations, and notifications.
Lead the full model lifecycle: from ideation and offline experimentation on large datasets to online deployment, A/B testing, and ongoing performance monitoring.
Develop and test novel modeling approaches, such as deep learning architectures and large language models (LLMs), to improve the home-shopping experience.
Apply cutting-edge AI techniques, including LLM-based retrieval and RAG-style systems, to create more natural and conversational property search experiences.
Optimize how and when homes are displayed to users, ensuring relevance and context in every interaction.
Collaborate with engineers, product managers, and designers to define, execute, and iterate on impactful projects.
Partner with data engineering and infrastructure teams to leverage large-scale distributed data systems for feature engineering and model training.
Requirements
Experienced in designing, training, and analyzing machine learning models to solve real-world business problems, not just academic benchmarks.
Proficient in Python and familiar with common ML libraries (e.g., PyTorch, TensorFlow, CatBoost, scikit-learn, Hugging Face) and distributed data systems (e.g., Spark, Hive, Databricks, Airflow).
Skilled in the scientific lifecycle: hypothesis formation, experiment design, result analysis, and clear communication to technical and non-technical partners.
Demonstrated experience in at least one of the following: search/information retrieval, personalized ranking/recommender systems, or generative AI/LLM-based systems.
Holds a PhD or Master’s degree in a relevant field (Computer Science, AI, Data Science, or related), or equivalent industry experience (typically 3-4+ years with a Master’s, or 1+ year with a PhD).
Comfortable working near production systems and collaborating closely with engineers and cross-functional partners.
Brings curiosity and excitement for applying generative AI and LLMs to transform the home-shopping experience.
Approaches challenges with ownership, scientific rigor, and a growth mindset.
Tech Stack
Airflow
Python
PyTorch
Scikit-Learn
Spark
Tensorflow
Benefits
In addition to a competitive base salary this position is also eligible for equity awards based on factors such as experience, performance and location.
Employees in this role will not be paid below the salary threshold for exempt employees in the state where they reside.