Data Scientist, Apple Pay Marketing (machine Learning Research)

Apple Apple · Big Tech · Cupertino, CA +1 · Machine Learning and AI

This role focuses on leveraging AI and ML, including LLMs, to build production-grade causal inference pipelines and ML-powered experiment analyses for marketing optimization within Apple Pay. The primary goal is to quantify marketing effectiveness, inform budget allocation, and identify customer response patterns through advanced ML techniques and generative AI tools.

What you'd actually do

  1. Design and implement marketing mix models and causal inference pipelines that quantify marketing effectiveness and inform budget allocation decisions.
  2. Build and execute incrementality tests, translating complex results into concrete, actionable campaign recommendations.
  3. Apply advanced ML techniques, such as segmentation, propensity modeling, and behavioral pattern recognition, to identify customer response patterns and inform audience strategy and experiment design.
  4. Partner with cross-functional teams to scope analytical problems, define success metrics, and deliver data-driven recommendations.
  5. Architect and maintain production-grade ML models and workflows that support ongoing marketing measurement and optimization.

Skills

Required

  • marketing science
  • marketing mix models
  • causal inference
  • incrementality measurement
  • marketing experiments
  • ML techniques
  • Python
  • pandas
  • NumPy
  • scikit-learn
  • statsmodels
  • SQL
  • Generative AI
  • large language models
  • communication skills

Nice to have

  • paid media data analysis
  • awareness marketing measurement
  • performance marketing measurement
  • emerging methodologies and tools
  • Generative AI applied to marketing workflows
  • M.S. or Ph.D. in Statistics, Machine Learning, Econometrics, Marketing Science, or a related quantitative field

What the JD emphasized

  • production-grade causal inference pipelines
  • production-grade ML models and workflows
  • Generative AI and LLM-based tools

Other signals

  • production-grade causal inference pipelines
  • ML-powered experiment analyses
  • Large Language Models (LLMs) to accelerate how insights are generated and communicated
  • Architect and maintain production-grade ML models and workflows
  • Leverage Generative AI and LLM-based tools to accelerate insight generation, automate reporting workflows, and streamline day-to-day analytical tasks