Analyze user behavior, content trends, and catalog data to generate insights that shape product decisions
Analyze and refine content classification and taxonomy systems to improve how content is grouped
Develop annotation-based evaluation frameworks, including sampling design and baseline definition, and assess the performance of LLMs used in annotation workflows
Develop and maintain metrics, dashboards, and text-to-SQL environments that support decision-making
Improve dataset quality and data transformations using SQL and DBT to ensure reliable reporting across content and behavioral domains

Experienced in analyzing complex datasets that combine user behavior with content and metadata signals
Developed metrics and reporting systems that support product or policy decision-making
Strong foundation in statistics and experience designing evaluation approaches in environments where controlled experiments are not feasible
Built annotation-based measurement frameworks, including sampling strategies and baseline definitions
Designed or applied methods to measure the quality of LLM-generated annotations
Proficient in SQL and have experience using DBT, Python, or R to build and maintain reliable analytical datasets
Communicate clearly and collaborate effectively with cross-functional teams

Data Scientist – Content Understanding

Key skills