About the role
About the Role
Build and own the data systems that turn messy sold-listing information into reliable comparable sales and price estimates. This role is central to the trustworthiness of pricing in a consumer resale marketplace, and you'll partner with computer vision teammates to define how items are matched across sources.
What You'll Do
* Build and maintain scheduled, large-scale ingestion pipelines for sold-listing data from multiple sources.
* Design entity resolution and deduplication systems that match inconsistent text and images to canonical items.
* Develop valuation logic that weighs comparable sales by recency, condition, and sample size.
* Create data quality monitoring to identify drift, potential fraud, and stale or unreliable comparisons.
* Collaborate with computer vision partners on matching standards across data sources with varying levels of detail.
* Evaluate build-versus-buy options for data sources, licensing, and third-party pricing feeds.
What We're Looking For
* At least 5 years of data engineering experience, including production ownership of large-scale ETL and data pipelines.
* Experience working with messy, adversarial data in a marketplace, pricing, fraud, or similarly noisy domain.
* Strong SQL skills and experience with modern data tools such as dbt, Airflow or Dagster, and Spark or similar technologies.
* Exposure to statistical estimation or pricing models, including basic regression-based comparable sales logic.
* Experience building data quality monitoring and large-scale entity resolution or record-linkage systems.
* Sound judgment on data quality tradeoffs, third-party data sources, and licensing decisions, plus the ability to explain pricing confidence and uncertainty to non-technical partners.
* Experience in pricing intelligence, real estate valuation, used-vehicle pricing, resale marketplaces, or early-stage startups is a plus.
Compensation & Benefits
Annual salary range: $160,000 to $220,000 USD.
Location
On-site in San Francisco, California, United States.