Senior Machine Learning Scientist - Personalization

Expedia Group•San Jose, CA

3d•$173,000 - $261,500

About The Position

Expedia Group is seeking a Senior Machine Learning Scientist to join the Unified Personalization Service team. This team is responsible for building Expedia Group's centralized, real-time personalization engine across brands and channels. The engine powers ranking, recommendations, retrieval, and other adaptive experiences to provide travelers with more relevant and useful interactions throughout their journey. The role involves shaping the next generation of deep learning systems for personalization, including recommendation, ranking, retrieval, traveler understanding, sequential modeling, and foundation-model-based personalization. This is a senior, hands-on applied science and engineering position requiring the ability to translate recent research into production-quality systems, influence technical direction, enhance the team's modeling capabilities, and mentor other scientists.

Requirements

Bachelor's degree in Computer Science or a related technical field; or Equivalent related professional experience
8+ years of relevant professional experience
Demonstrated ownership of machine learning solutions at the service or multi-service level, including problem definition, model development, evaluation, and operationalization within a product or technical domain
Strong foundation in machine learning methods, statistical analysis, experimentation, and data-driven decision making, with hands-on coding experience in scientific and production-oriented environments
Experience working with cross-functional partners to deploy technical solutions, with core expectations in scalable model development, data modeling, and integration into software systems

Nice To Haves

Advanced degree in Machine Learning, Computer Science, Statistics, Mathematics, Engineering, or a related quantitative field
Experience delivering machine learning solutions at scale, including architecture considerations, production monitoring, model lifecycle management, and operational excellence in live environments
Demonstrated ability to influence technical direction within a domain through rigorous experimentation, strong scientific reasoning, pragmatic solution design, and clear communication with cross-functional partners
Strong experience with recommendation, ranking, retrieval, search, personalization, ads, marketplace, e-commerce, or similarly complex applied ML systems
Experience with neural recommendation systems, sequential or session-based recommendation, transformer-based recommenders, semantic retrieval, generative retrieval, or representation learning at scale
Experience with foundation models, LLMs, embedding models, semantic IDs, hybrid LLM-recommender systems, two-stage retrieval and ranking systems, or retrieval-augmented personalization workflows
Relevant academic publications, patents, open-source contributions, technical blog posts, industry talks, or other contributions to the ML/recommender-systems community

Responsibilities

Design, develop, and apply machine learning solutions to real-world personalization, product, and business problems, translating ambiguous opportunities into scalable models, experiments, and production-ready capabilities.
Drive end-to-end scientific work across problem formulation, data exploration, feature engineering, model development, evaluation, and iteration, with strong attention to measurable impact.
Partner closely with engineers, product, and business stakeholders to integrate machine learning solutions into services and workflows, including system design, API design, and data modeling considerations where applicable.
Use strong technical judgment to select appropriate methods, validate outcomes, and improve model performance, reliability, and operational quality across multiple problem domains.
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.
Contribute deep technical expertise across related domains, helping raise scientific and engineering quality through experimentation, documentation, mentoring, and reusable approaches that support broader team effectiveness.