Catalog Operations Analyst II

Instacart Instacart · Consumer · Canada · Remote · Analytics

Instacart is seeking a Catalog Operations Analyst II to drive data quality and enrichment for the Health and Meals pillar. This role involves designing and operationalizing LLM pipelines, performing SQL analyses, managing external vendors, and partnering with cross-functional teams to improve product data across the Instacart ecosystem. The ideal candidate has experience in catalog operations, data quality, SQL, and familiarity with LLMs and prompt design.

What you'd actually do

  1. Own data quality outcomes for the Health and Meals pillar by defining accuracy and coverage goals for critical attributes (e.g., nutrition, dietary tags, allergens, preparation/meal context) and driving measurable improvements across the catalog.
  2. Design, test, and operationalize LLM pipelines in partnership with Catalog Engineering and ML, including prompt iterations, evaluation frameworks, and human-in-the-loop QA.
  3. Develop robust SQL analyses to monitor health of the catalog, identify root causes, prioritize fixes, and communicate performance and impact to cross-functional stakeholders.
  4. Establish and continuously refine taxonomies, attribute definitions, and normalization standards; author SOPs and quality guidelines that scale across internal teams, external content providers, and BPOs.
  5. Manage day-to-day execution with external vendors and data partners (e.g. BPOs), setting SLAs, creating QA workflows, and implementing sampling plans that improve precision and recall at scale.

Skills

Required

  • 3+ years of experience in catalog/content operations, data operations, or data quality within e-commerce, marketplace, retail, or a similar high-scale data environment.
  • Bachelor’s degree in a quantitative, analytical, or related field (e.g., Data/Information Science, Business, Economics, Statistics) or equivalent practical experience.
  • Demonstrated success partnering with Engineering, Data Science, and Product to scope requirements and deliver production-scale projects.
  • Proficiency in SQL (including joins, aggregations, and window functions) and advanced Excel/Google Sheets for analysis, QA sampling, and reporting.
  • Familiarity with LLMs and prompt design for data extraction, classification, or attribute enrichment, including LLM evaluation and feedback loops.
  • Hands-on experience defining and managing data quality metrics (e.g., accuracy, precision, recall) and running root cause analyses.
  • Experience operationalizing workflows with external vendors/BPOs or data providers, including SOPs, SLAs, and multi-step QA processes.

Nice to have

  • Experience using AI tools (e.g. Claude Code, Codex) in your day to day.
  • Experience with data wrangling, QA automation, and scaling manual processes.
  • Experience building dashboards in Looker, Tableau, or Mode to track operational and quality KPIs.
  • Track record of delivering results in dynamic, ambiguous environments while communicating effectively with technical and non-technical audiences.
  • Background in ecommerce, grocery/CPG data, or technology/startups.

What the JD emphasized

  • LLM pipelines
  • evaluation frameworks
  • human-in-the-loop QA
  • LLM evaluation and feedback loops

Other signals

  • AI-first operations team
  • LLM-driven pipelines
  • data quality and enrichment