Machine Learning Scientist II - Agentic Experiences

In Expedia's Traveler Discovery & Planning team, you design and deploy agentic AI systems that autonomously plan, reason, and collaborate with sub-agents and tools. You work with product, engineering, and research to deliver production-grade solutions that enhance traveler experiences at scale. You explore cutting-edge techniques and ensure safe, reliable performance across real-world tasks. This role offers the chance to shape AI-driven travel assistance under Expedia's AI-first vision.

• medical, dental, and vision coverage
• paid time off
• Employee Assistance Program
• wellness and travel reimbursement
• travel discounts
• IATAN membership

• Design, build, and evaluate multi-step agentic AI systems with autonomy, planning, tool use, memory management, and multi-agent collaboration
• Research and implement modern agentic architectures (e.g., ReAct, reflection loops, chain-of-thought prompting, tool-augmented reasoning)
• Develop and maintain agent orchestration frameworks for task decomposition, sub-agent delegation, and failure handling
• Integrate large language models with external tools, APIs, databases, and code execution environments for real-world tasks
• Define and own evaluation frameworks to measure task success, reliability, latency, cost, and safety
• Collaborate with product, engineering, and research teams to translate requirements into deployable agentic designs
• Identify and mitigate risks in agentic systems (prompt injection, unintended actions, hallucination, unsafe tool use)
• Stay current with the evolving agentic AI landscape and synthesize research to steer technical direction

• PhD, MS, or BS in Computer Science, Machine Learning, Statistics, Engineering, or related field, or equivalent professional experience
• 2+ years of industry experience
• Proven experience designing and deploying agentic or multi-step AI systems (e.g., ReAct, tool-calling agents, multi-agent pipelines) in production or research
• Proficiency in Python and ML frameworks (PyTorch, TensorFlow, or JAX); experience with LLM APIs and orchestration libraries (e.g., LangChain, LlamaIndex)
• Experience integrating LLMs with external tools, APIs, and structured data sources for real-world task completion
• Understanding of prompt engineering (chain-of-thought, few-shot prompting, structured output)
• Experience defining and running evaluation frameworks for ML systems (offline benchmarking, production monitoring)

• strong collaboration and cross-functional teamwork
• effective communication of complex ideas
• problem-solving mindset and curiosity
• Python
• PyTorch
• TensorFlow