About this role
About the Role YipitData’s Corporate Retail & Brands team collaborates with brands to deliver comprehensive consumer category insights. The Data Classification Associate will own data quality at the item level, resolve definitional and methodological issues in category hierarchies, and help build scalable product taxonomies for retail datasets. This remote-friendly role requires East Coast work hours and offers exposure to clients and rapid growth in a fast-paced environment. What You'll Do
- Own category hierarchies end-to-end — become the primary owner of high-impact hierarchies, focusing on accuracy, client value, and efficiency.
- Build and refine product taxonomies — develop new category hierarchies across large retail datasets (millions of SKUs).
- Become a true category expert — develop deep knowledge of products, brands, and how they should be classified; build rules and methodologies rooted in domain expertise.
- Drive AI-enabled classification — translate existing mapping solutions into scalable AI-enabled approaches that improve speed and consistency.
- Design and run QA processes — create QA processes that catch error patterns missed by LLMs and human review.
- Investigate and resolve data quality issues — diagnose and fix complex data quality problems, including definitional and methodological challenges in our hierarchies.
- Be the client-facing expert on category data — serve as a trusted resource for internal and external stakeholders; explain definitions, limitations, and coverage.
- Collaborate cross-functionally — partner with Insights, Sector Data, Data Validation, and Engineering to align on best practices and streamline workflows.
- Innovate and mentor — identify opportunities to improve efficiency and data quality; establish robust processes and raise quality standards. What We're Looking For
- 3-5 years of experience in data analytics, data operations, category mapping, or consulting
- 2+ years of experience with SQL, Python, PySpark, or other programming languages to explore and transform large, complex datasets
- Familiarity with GitHub and Databricks
- Ability to communicate complex problems in simple terms to internal and external stakeholders
- Comfortable thriving in ambiguity and rapid growth
- East Coast work hours