DATA SCIENTIST LEAD

5 days ago

Seattle, WA, United States Talent Groups Full-time

What they’ll do

  • Validate the score against customer outcomes such as churn and care contacts
  • Build and optimize large-scale data pipelines in Databricks
  • Catch and fix data quality issues before results reach leadership
  • Document methodology, data lineage, and logic changes
  • Explain findings to non-technical and executive audiences

Must-haves:

  • Python/PySpark and advanced SQL
  • Databricks performance tuning (partitioning, Delta optimization, cluster sizing)
  • Applied statistics, especially predictive modeling for yes/no outcomes like churn
  • Git/version control and production-quality coding habits
  • Habit of checking whether results make sense as they work; skeptical of results that look too good
  • Strong documentation and organizational discipline

Strong preferences

  • Weight of Evidence/Information Value (WoE/IV) experience
  • Wireless or telecom network KPI knowledge
  • Snowflake experience
  • Experience building composite scores, indices, or scorecards