Senior Applied Scientist , Prime Video Ads

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

Senior Applied Scientist role focused on building and deploying ML models for personalizing advertising experiences on Prime Video. The role involves research and development across the ML lifecycle, from exploratory research to production deployment, with a focus on understanding heterogeneous customer responses, inferring preferences from indirect signals, and optimizing for competing objectives like revenue and customer engagement at massive scale.

What you'd actually do

  1. Lead the research and development of ML models that personalize advertising decisions for 100M+ customers across 100k+ titles, with production deployment in mind
  2. Develop deep learning architectures (multi-task learning, embedding-based representations) for customer behavior prediction at scale
  3. Design and analyze large-scale A/B experiments, applying causal inference techniques to measure and optimize the impact of ad strategies on customer engagement and monetization
  4. Partner with engineering to ensure models meet production latency and scalability requirements
  5. Collaborate with product managers to frame business problems as tractable ML problems and translate findings into product decisions

Skills

Required

  • building machine learning models for business application
  • neural deep learning methods
  • machine learning
  • Python

Nice to have

  • large scale distributed systems
  • Hadoop
  • Spark
  • PyTorch
  • JAX
  • Machine Learning fundamentals
  • Large Language Model fundamentals
  • architecture
  • training/inference lifecycles
  • optimization of model execution

What the JD emphasized

  • building machine learning models for business application experience
  • neural deep learning methods and machine learning
  • large-scale A/B experiments
  • causal inference techniques

Other signals

  • personalization at scale
  • ML models for business application
  • deep learning architectures
  • large-scale A/B experiments
  • causal inference techniques