Machine Learning Scientist III - Agentic Experiences
About The Position
Expedia Group’s Traveler Discovery & Planning team is building AI-driven agentic systems to improve customer experiences, increase engagement, and strengthen traveler relationships. The role focuses on creating autonomous, intelligent agent systems for conversational assistance and personalized trip planning, with solutions that can affect travelers from the discovery stage through booking and beyond. The Machine Learning Scientist will design, build, and evaluate multi-step agentic AI systems, research agent architectures and reasoning techniques, and develop orchestration frameworks for task decomposition, delegation, failure handling, and recovery. The role also integrates large language models with tools, APIs, databases, and code execution environments; establishes evaluation frameworks; collaborates with product, engineering, and research teams to deliver production-grade systems; and identifies and mitigates safety and reliability risks. The position requires keeping current with agentic AI research and industry developments to inform technical direction.
Requirements
- PhD, MS, or BS in Computer Science, Machine Learning, Statistics, Engineering, or a related field, or equivalent professional experience.
- At least 5 years of related industry experience.
- Demonstrated experience designing and deploying agentic or multi-step AI systems, such as ReAct, tool-calling agents, or multi-agent pipelines, in production or research settings.
- Strong proficiency in Python and ML frameworks such as PyTorch, TensorFlow, or JAX.
- Experience with LLM APIs and orchestration libraries such as LangChain, LlamaIndex, 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 ML system evaluation frameworks, including offline benchmarking and production monitoring.
Nice To Haves
- Experience in the travel or e-commerce industry.
- Publications in top-tier ML conferences or journals.
- Patented inventions, pending or issued.
- Contributions to open-source ML projects.
- Experience taking models from prototype to production in collaboration with Machine Learning Engineering teams.
Responsibilities
- Design, build, and evaluate multi-step agentic AI systems, including autonomous agents with planning, tool use, memory management, and multi-agent collaboration.
- Research and implement agentic architecture techniques such as ReAct, reflection loops, chain-of-thought prompting, and tool-augmented reasoning.
- Develop and maintain agent orchestration frameworks for task decomposition, sub-agent delegation, failure handling, and recovery.
- Integrate large language models with external tools, APIs, databases, and code execution environments to enable real-world task completion.
- Define and own evaluation frameworks that measure task success, reliability, latency, cost, and safety across benchmarks and production scenarios.
- Collaborate with product, engineering, and research teams to translate business requirements into agentic system designs and production-grade solutions.
- Identify and mitigate agentic-system risks, including prompt injection, unintended actions, hallucinations in long-horizon tasks, and unsafe tool use.
- Monitor developments in agentic AI research and industry and use them to inform the team's technical direction.
Benefits
- Medical coverage.
- Dental coverage.
- Vision coverage.
- Paid time off.
- Employee Assistance Program.
- Wellness and travel reimbursement.
- Travel discounts.
- International Airlines Travel Agent Network (IATAN) membership.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
