Machine Learning Scientist II

Expedia Expedia · Hospitality · Geneva, Switzerland

Expedia Group is seeking an ML Scientist II to join their Revenue Optimization ML team. The role involves building end-to-end ML solutions for ranking, recommendation engines, and optimizing pricing and commission offerings. Responsibilities include developing and implementing ML models for dynamic pricing, demand forecasting, and revenue optimization, collaborating on end-to-end solutions from data preprocessing to production deployment, and participating in A/B testing and experiment design. The ideal candidate has a strong foundation in ML and engineering, with experience in Python, PySpark, and common ML libraries, and familiarity with big data technologies and cloud platforms.

What you'd actually do

  1. Develop and implement ML models for dynamic pricing, demand forecasting, and revenue optimization
  2. Collaborate on end-to-end solutions, from data preprocessing to model deployment in production environments
  3. Participate in A/B testing and experiment design to continuously improve our algorithms
  4. Analyze complex datasets to derive actionable insights for business stakeholders
  5. Contribute to the team's technical capabilities by staying current with the latest ML techniques and technologies

Skills

Required

  • Python
  • PySpark
  • scikit-learn
  • TensorFlow
  • Keras
  • Hadoop
  • Spark
  • AWS
  • GCP
  • machine learning algorithms
  • statistics
  • probability theory
  • problem-solving
  • communication skills

Nice to have

  • Ph.D.
  • 2 years of industry experience in applying ML to real-world problems

What the JD emphasized

  • builds end-to-end ML solutions for ranking problems, recommendation engines as well as optimizing our pricing and commission offerings
  • Revenue Optimization ML team
  • ML models for dynamic pricing, demand forecasting, and revenue optimization
  • end-to-end solutions
  • model deployment in production environments
  • applying ML to real-world problems

Other signals

  • ML models for dynamic pricing
  • demand forecasting
  • revenue optimization
  • end-to-end solutions
  • model deployment in production environments
  • A/B testing and experiment design
  • applied machine learning at scale