Machine Learning Scientist II

Our Expedia Product & Technology division builds innovative products, services, and tools to deliver high-quality experiences for travelers, partners, and our employees. A unified, singular technology platform powered by data and machine learning provides secure, differentiated, and personalized experiences for the traveler and our partners that drive loyalty and customer satisfaction.   
 

The Machine Learning Scientist II role sits on the Lodging Search Ranking AI team in the Expedia Product & Technology division of Expedia Group. At the heart of the 3-side marketplace (the traveler, the property owners and the platform), this team develops and optimizes ranking models  with state-of-the-art machine learning / genAI techniques to power lodging search and personalized lodging ranking/recommendations for the multiple brands and lines of business in our portfolio.  

In this role, your expertise and passion for innovation, developing cutting-edge technology and implementing industry-leading solutions, will improve the experience of millions of travelers and travel partners each year. This is an applied scientist role: your models will be deployed to our production systems, and your results will be measured objectively via A/B testing, directly impacting our business results. We collaborate closely with the analytics, product, and engineering teams.  

In this role, you will: 

• Develop, implement, and optimize machine learning models that power data‑driven features and products, from problem framing through production deployment and iteration. 

• Design and evaluate experiments, offline evaluations, and A/B tests to measure model impact, using statistical rigor to compare alternatives and drive decisions. 

• Collaborate with engineers, product managers, and analysts to translate ambiguous business problems into well‑scoped ML solutions, including data requirements, modeling approach, and success metrics. 

• Apply strong data modeling, feature engineering, and model selection skills across multiple domains, ensuring models are robust, explainable, and performant at scale. 

• Safely integrate and operate AI/ML‑enabled solutions that improve outcomes, including monitoring model performance, detecting degradation, and driving continuous improvements in production. 

• Demonstrate familiarity with AI‑driven systems, tools, or workflows and applying AI/ML concepts to real‑world products, contributing reusable methodologies and best practices that can be leveraged across teams and problem spaces. 

Minimum Qualifications: 

• Bachelor’s degree in Computer Science or a related technical field; or Equivalent related professional experience. 

• 2+ years of relevant professional experience. 

• Proven ability to own ML solutions for a well‑defined service or product area, including data exploration, model development, offline and online evaluation, and partnering with engineering for integration. 

• Proficiency in at least one major programming language used for ML (such as Python) and common ML/AI frameworks and tooling for model development, training, and evaluation. 

• Solid grounding in core ML concepts (e.g., supervised and unsupervised learning, model generalization, overfitting, evaluation metrics), and experience working with real‑world, noisy datasets. 

Preferred Qualifications: 

• Advanced degree (Master’s or PhD) in a quantitative field with a focus on machine learning, statistics, or AI, with experience applying research ideas to practical, large‑scale problems. 

• Experience designing and operating ML systems at scale, including feature pipelines, model training workflows, and online inference, with attention to latency, reliability, and cost. 

• Demonstrated track record of leading the end‑to‑end lifecycle of ML solutions within a product or domain, from ideation and prototyping through experimentation, launch, and ongoing optimization. 

• Strong background in experimentation and data‑driven decision making, including designing robust A/B tests, interpreting results, and translating findings into product and model changes. 

• Familiarity with AI‑driven systems, tools, or workflows and applying AI/ML concepts to real world products, including experience with at least one of: recommendation systems, ranking, search, personalization, forecasting, or optimization models.