Data Scientist

Summary

Zillow is a real estate technology company that provides products and services for buying, selling, financing, renting, and agent productivity. The Data Scientist will lead end-to-end analytics and data science projects for the Partner Analytics team, developing models, experiments, and data products to improve business decisions and customer experiences.

Responsibilities

• Independently scope and deliver end-to-end data science projects, from problem framing through model development, validation, and productionization
• Build and maintain industry performance and customer segmentation models, applying appropriate techniques (e.g., clustering, regression, tree-based models) and ensuring they are robust, interpretable, and actionable
• Partner with Data Engineering and ML Engineering to deploy and maintain models in production, including feature development, batch/real-time scoring, and monitoring model performance over time
• Design and analyze experiments and observational studies (A/B testing, causal inference) to evaluate product features and business initiatives
• Translate ambiguous business problems into well-defined analytical approaches, selecting appropriate methodologies and success metrics
• Provide data-driven recommendations to leaders, clearly communicating trade-offs, assumptions, and impact
• Collaborate with cross-functional teams including Follow Up Boss, Preferred, and zPro to align on goals, define KPIs, and deliver integrated insights
• Contribute to scalable data assets (clean datasets, metrics definitions, dashboards) that enable self-service analytics

Skills

• 3–5+ years of experience in data science, applied machine learning, or a related field
• Strong foundation in **statistics, machine learning, and experimentation**, with demonstrated ability to apply methods to real-world business problems
• Proficient in **Python (pandas, scikit-learn, PySpark**) and **SQL**; comfortable working with large datasets in modern data platforms (e.g., Snowflake, Spark)
• Experience building **performance models and data products**
• Familiarity with **production workflows** (e.g., Airflow, dbt, model deployment patterns, monitoring)
• Ability to **work independently in ambiguous spaces** while maintaining alignment with stakeholders
• Strong communication skills, with the ability to tailor insights to technical and non-technical audiences
• Experience collaborating across multiple product and business teams and translating outputs into business insights
• U.S. employees may live in any of the 50 United States, with limited exceptions

Qualifications

Must Haves

• 3–5+ years of experience in data science, applied machine learning, or a related field
• Strong foundation in **statistics, machine learning, and experimentation**, with demonstrated ability to apply methods to real-world business problems
• Proficient in **Python (pandas, scikit-learn, PySpark**) and **SQL**; comfortable working with large datasets in modern data platforms (e.g., Snowflake, Spark)
• Experience building **performance models and data products**
• Familiarity with **production workflows** (e.g., Airflow, dbt, model deployment patterns, monitoring)
• Ability to **work independently in ambiguous spaces** while maintaining alignment with stakeholders
• Strong communication skills, with the ability to tailor insights to technical and non-technical audiences
• Experience collaborating across multiple product and business teams and translating outputs into business insights
• U.S. employees may live in any of the 50 United States, with limited exceptions

Benefits

• This position is also eligible for equity awards based on factors such as experience, performance and location.
• Remote employees may work from a physical location of their choice, which must be identified to the Company.
• Most employees have the flexibility to work from wherever they’re most productive.