Build the data foundation for pricing in an early-stage internet marketplace. You will turn noisy sold-listing data into reliable comparable items and price estimates, helping users and investors understand both the value and confidence of each estimate.
Build and own scheduled ingestion pipelines for sold-listing data from multiple marketplaces and external sources.
Design entity resolution systems that match inconsistent listing text and images to canonical items.
Develop valuation logic that weights comparable listings by recency, condition, and quantity.
Create production monitoring to detect data drift, fraud, stale comparisons, and integrity issues.
Partner with computer vision teammates to define how items are matched across sources with varying detail.
Make build-versus-buy decisions about data sources, licensing, and third-party pricing feeds.
At least 5 years of data engineering experience, including ownership of large-scale production ETL and data pipelines.
Strong SQL skills and experience with a modern data stack such as dbt, Airflow or Dagster, and Spark or similar tools.
Experience working with noisy or adversarial data in marketplaces, pricing, fraud, or a related domain.
Experience with statistical estimation or pricing models, including regression-based comparable sales logic.
Experience building entity resolution or record-matching systems at scale, plus production data quality monitoring.
Ability to make sound data quality tradeoffs and explain pricing confidence and uncertainty to non-technical stakeholders.
Experience processing data from multiple external sources and evaluating data products or integrations is valuable.
Pricing intelligence, data licensing, and early-stage startup experience are helpful.
Base salary: $160,000 to $220,000 annually. Visa sponsorship is not available.
Hybrid, New York, New York, United States.