Senior Machine Learning Scientist - Agentic

At Expedia Group, we help travelers explore the world, one journey at a time. As a global travel company powered by passionate people, trusted partnerships, and leading technology, we connect travelers, partners, and advertisers through our consumer brands, B2B network, and travel advertising business.

Here, you'll do meaningful work that helps millions of people discover, book, and experience travel with more ease, confidence, and joy. Our five Behaviors – Traveler First, Think Big, Operate with Excellence, Ownership Mindset, and Succeed Together – help foster a supportive environment where people can grow their careers and have the flexibility, benefits, and support to do their best work.

Join us and build for travelers everywhere.

Expedia Technology teams partner with our Product teams to create innovative products, services, and tools to deliver high-quality experiences for travelers, partners, and our employees. A singular technology platform powered by data and machine learning provides secure, differentiated, and personalized experiences that drive loyalty and traveler satisfaction.

The Traveler Discovery & Planning team at Expedia is at the forefront of innovation in AI-driven agentic systems. We’re dedicated to enhancing customer experiences, increasing engagement, and strengthening traveler relationships through cutting‑edge machine learning solutions. Our work directly impacts millions of travelers worldwide, shaping their journey from dreaming to booking and beyond.

Join a team that’s focused on Agentic Experiences revolutionizing traveler experiences through autonomous, intelligent agent systems. From building cutting‑edge conversational AI that anticipates traveler needs to developing proactive solutions for personalized trip planning, your work will shape the future of travel assistance and directly impact millions of users worldwide. This is a rare opportunity to build foundational systems in a high‑impact domain, backed by Expedia’s AI‑first vision.

• Design, build, and evaluate multi‑step agentic AI systems, including autonomous agents capable of planning, tool use, memory management, and multi‑agent collaboration
• Research and implement state‑of‑the‑art techniques in agentic architectures, such as ReAct, reflection loops, chain‑of‑thought prompting, and tool‑augmented reasoning
• Develop and maintain agent orchestration frameworks, defining how agents decompose tasks, delegate to sub‑agents, and handle failure and recovery
• Integrate large language models (LLMs) with external tools, APIs, databases, and code execution environments to enable real‑world task completion
• Define and own evaluation frameworks for agentic systems, measuring task success, reliability, latency, cost, and safety across diverse benchmarks and production scenarios
• Collaborate closely with product, engineering, and research teams to translate business requirements into agentic system designs and deliver production‑grade solutions
• Identify and mitigate risks specific to agentic systems, including prompt injection, unintended actions, hallucination in long‑horizon tasks, and unsafe tool use
• Stay current with the rapidly evolving agentic AI landscape, synthesizing academic research and industry developments to inform the team’s technical direction
• Mentor junior ML engineers and scientists, providing technical guidance on agentic design patterns, LLM best practices, and experimentation methodology

• 8+ years of related industry experience
• Demonstrated experience designing and deploying agentic or multi‑step AI systems (e.g., ReAct, tool‑calling agents, multi‑agent pipelines) in production or research settings
• Strong proficiency in Python and ML frameworks (PyTorch, Tensor Flow, or JAX); experience with LLM APIs and orchestration libraries (e.g., Lang Chain, Llama Index, or similar)
• Experience integrating LLMs with external tools, APIs, and structured data sources for real‑world task completion
• Solid understanding of prompt engineering techniques including chain‑of‑thought, few‑shot prompting, and structured output generation
• Experience defining and running…