Senior Machine Learning Scientist - Crm Marketing

Expedia Expedia · Hospitality · Seattle, WA

Senior Machine Learning Scientist role focused on building and owning production ML systems for CRM marketing personalization at Expedia Group. The role involves defining the ML roadmap, leading the full lifecycle of ML systems from problem framing to deployment, partnering with business and engineering teams, evolving experimentation, communicating findings, and mentoring junior scientists. The focus is on driving retention, reactivation, and growth through ML-driven personalization at scale.

What you'd actually do

  1. Help define the ML science roadmap: Identify the highest-impact ML opportunities for CRM personalization, sequence initiatives against business strategy, and translate a multi-year vision into concrete, deliverable projects with clear milestones and measurable outcomes.
  2. Build and own production ML systems: Lead the full lifecycle — from problem framing and metric design through data exploration, modeling, evaluation, deployment, and iteration — for systems that run daily at scale, in partnership with engineering.
  3. Partner across the business: Work with marketing to understand customer and campaign objectives, with analytics to shape measurement strategies, and with engineering to deliver reliable production systems — bringing business acumen and domain depth to every technical decision.
  4. Evolve experimentation and measurement: Strengthen how we test hypotheses and quantify impact — finding smarter, faster ways to validate ideas, reduce uncertainty, and build confidence in ML-driven decisions before and after they reach production.
  5. Tell the data story: Communicate findings, trade-offs, and recommendations clearly to technical and business audiences through effective data visualization and narratives that influence priorities and build stakeholder confidence.

Skills

Required

  • Python
  • SQL
  • distributed data processing (Spark/Databricks)
  • solid software engineering practices
  • modern AI development tools
  • applying machine learning to real-world problems
  • experimentation and statistics fundamentals
  • designing rigorous experiments (A/B and beyond)
  • producing reliable, accurate analyses

Nice to have

  • constrained optimization
  • operations research
  • budget allocation methods
  • causal inference
  • CRM personalization
  • loyalty marketing
  • incentive optimization
  • customer retention systems
  • deep learning
  • reinforcement learning
  • multi-armed bandits
  • customer lifetime value modeling
  • churn prediction
  • propensity scoring
  • CI/CD for ML
  • model monitoring
  • observability
  • automated pipelines

What the JD emphasized

  • track record of delivering production ML systems that created measurable business impact
  • Leader of cross-functional ML projects
  • Deep understanding of causal inference

Other signals

  • ML systems behind personalized CRM offers
  • models determine which customers to reach, when to engage them, and what incentive to offer
  • powering retention, reactivation, and growth campaigns
  • fully ML-driven personalization at scale
  • define that technical roadmap