Machine Learning Scientist III - Package Pricing

Expedia Expedia · Hospitality · Seattle, WA

Machine Learning Scientist III focused on Package Pricing at Expedia Group. The role involves designing, building, and improving ML models and systems for a scalable, intelligent pricing system. Responsibilities include end-to-end model development, data pipeline creation, and partnering with cross-functional teams to translate business problems into ML solutions. The role also touches on causal inference and optimization techniques.

What you'd actually do

  1. Design, build, and improve ML models and systems that power Expedia Group products, with a focus on measurable business and customer impact
  2. Perform end-to-end model development, including problem formulation, data exploration, feature engineering, training, evaluation, and deployment in production environments
  3. Develop robust data pipelines, data transformations, and data quality checks to ensure high-quality input signals for ML models and experimentation
  4. Partner with product, engineering, and analytics teams to translate business problems into ML solutions, define success metrics, and run experiments to validate impact
  5. Safely integrate and operate AI/ML‑enabled solutions that improve outcomes, including familiarity with AI-driven systems, tools, or workflows and applying AI/ML concepts to real world products

Skills

Required

  • Python
  • data processing frameworks
  • model training libraries
  • model evaluation techniques
  • owning ML components or services in production
  • monitoring model performance
  • maintaining data pipelines
  • collaborating with engineering teams on APIs and data models

Nice to have

  • Advanced degree (master’s or PhD) in a quantitative discipline
  • pricing, revenue optimization, marketplace dynamics, or similar business problems
  • designing and analyzing experiments (e.g., A/B testing)
  • working with noisy or incomplete data
  • building ML models using user behavior, segmentation, or contextual signals
  • causal inference methods
  • optimization techniques (e.g., mixed-integer programming)

What the JD emphasized

  • end-to-end model development
  • deployment in production environments
  • ML models and systems
  • pricing, revenue optimization

Other signals

  • end-to-end model development
  • deployment in production environments
  • ML models and systems
  • pricing, revenue optimization