Principal Machine Learning Scientist - Principal Machine Learning Scientist – Generative AI & Fraud

Overview

Expedia Group brands power global travel for everyone, everywhere. We design cutting-edge tech to make travel smoother and more memorable, and we create groundbreaking solutions for our partners. Our diverse, welcoming community is essential in driving our success.

Why Join Us? To shape the future of travel, people must come first. Guided by our Values and Leadership Agreements, we foster an open culture where everyone belongs, differences are celebrated, and we know that when one of us wins, we all win.

We provide a full benefits package, including exciting travel perks, generous time off, parental leave, a flexible work model (with some pretty cool offices), and career development resources to fuel our employees  passion for travel and ensure a rewarding career journey. We’re building a more open world. Join us.

Are you passionate about using machine learning to outsmart fraud and protect travelers without adding friction? Would you like to work in the fast-paced, adversarial, high-scale, and data-rich world of online travel risk?

The Fraud & Risk team plays a pivotal role in safeguarding the company’s finances, thwarting billions of dollars in fraudulent attacks annually. Our efforts extend beyond financial security—we combat threats such as phishing, counterfeit vacation rental schemes, improper payment diversions, and unauthorized access to personal and payment card information. By ensuring a secure environment, the team fosters trust among travelers and providers, enabling Expedia’s sustained revenue growth.

This is a rare chance to build a simpler, more explainable and adaptive decisioning platform in a live, scaled environment. We are looking for a hands-on Principal Scientist to help us build and execute a high-visibility, high-impact vision to dramatically improve auto-prevention rates, reduce ops queuing, and apply novel techniques using Generative AI in the evolving, adversarial world of fraud.

Machine Learning Engineering

• Configure, maintain, and optimize storage and processing environments (cloud, on-premises, cluster management, etc.).
• Build production-grade data and machine learning pipelines that support batch and streaming applications.
• Advocate for software design best practices and demonstrate the ability to construct robust data and machine learning pipelines.

Machine Learning / Data Science

• Perform applied research to consistently achieve desired solution performance and improve organizational capabilities.
• Demonstrate an in-depth understanding of all aspects of learning theory.
• Support leaders in setting up frameworks for the machine learning development lifecycle and devise machine learning strategies.
• Advise business leaders in complex settings to create and enable robust machine learning solutions with high impact, at an expert level.
• Lead and mentor others in all machine learning activities.

Generative AI

• Deep expertise in LLM fine-tuning and prompt engineering (e.g., OpenAI APIs, Hugging Face, Anthropic Claude, Google Gemini).
• Strong experience with AI orchestration tools (e.g., Lang Chain, Llama Index, vector databases for retrieval augmentation).
• Hands-on knowledge of function calling and API-based reasoning models (e.g., using structured outputs to drive automated workflows).
• Proficiency in Python and AI development frameworks for building scalable AI applications.
• Understanding of multi-agent architectures and best practices in agentic AI design.
• Experience with real-world AI evaluation techniques, including golden sets, synthetic data generation, and interactive testing

Statistics

• Leverage a solid theoretical foundation and apply advanced statistical methods to a broad range of problems.
• Demonstrate experience in advanced experimental design (e.g., adaptive designs).
• Read relevant publications in the field and implement described methods to business problems.
• Act as a technical mentor for junior profiles.

Model Design

• Design end-to-end models based on a detailed understanding of business requirements, including general approach, choice of algorithm, and data sources.
• Experience applying sequential models (e.g., RNNs, Transformers)…