Data Scientist , Prime Video - Advertising

Amazon Amazon · Big Tech · Arlington, VA · Data Science

Data Scientist role focused on building and guiding data-driven frameworks for ad experience personalization, yield optimization, and monetization within Prime Video. This involves using advanced statistical and machine learning techniques on large-scale data, designing end-to-end data science workflows, building and maintaining statistical models for various ad-related predictions, and partnering with product and economics teams to design experiments and measure impact. The role aims to improve customer experience and advertiser results, supporting hundreds of millions of users.

What you'd actually do

  1. Use advanced statistical and machine learning techniques to extract insights from large-scale streaming, ad delivery, and auction data sets.
  2. Design and implement end-to-end data science workflows from data acquisition and cleaning through model development, offline evaluation, A/B testing, and production deployment in partnership with product and engineering teams
  3. Build, validate, and maintain the statistical models that support the roadmap including Supply tier classification and Supply Quality Index, ad tolerance and fatigue scoring, and propensity and disengagement prediction
  4. Partner with product and economist teams to design hold out experiments to measure impact of Ad load on revenue and customer engagement; define north star metrics, power calculations, holdout structures, and promotion gates for every major lever.
  5. Support scalable, self-service analytics by building curated datasets for PVa product, ops, sales, and science covering supply, yield, CX, and advertiser diversification outcomes.

Skills

Required

  • 5+ years of data querying languages (e.g. SQL), scripting languages (e.g. Python) or statistical/mathematical software (e.g. R, SAS, Matlab, etc.) experience
  • 4+ years of data scientist experience
  • Experience with statistical models e.g. multinomial logistic regression
  • Experience with statistical methods (e.g., A/B Testing, Regression)

Nice to have

  • 2+ years of data visualization using AWS QuickSight, Tableau, R Shiny, etc. experience
  • Experience managing data pipelines
  • Experience as a leader and mentor on a data science team

What the JD emphasized

  • end-to-end ownership
  • data-driven frameworks
  • ML prediction platform
  • experimentation platform
  • advanced statistical and machine learning techniques
  • model development
  • offline evaluation
  • A/B testing
  • production deployment
  • statistical models
  • hold out experiments
  • measure impact
  • scalable, self-service analytics
  • curated datasets

Other signals

  • ML prediction platform
  • personalization
  • yield
  • monetization
  • customer experience
  • advertiser results