Lead Agentic AI Scientist for Multi‑Step Systems

11105 Expedia, Inc.; Seattle (WA); On-site; USD 224,000 - 314,000; Full time

Benefits offered by this job

Medical, dental, vision

Paid time off

Travel discounts

IATAN membership

Job summary

Expedia Group seeks an experienced engineering leader to design and deploy agentic, multi-step AI systems that can plan, use tools, and collaborate across sub‑agents. You will explore ReAct, reflection loops, and prompt engineering while coordinating with product and research teams in Seattle.

The role requires 10+ years in ML, strong Python skills, and a track record of production ML deployments. Competitive pay and full benefits accompany a hybrid work model in the Seattle area.

Qualifications

• BS in Computer Science, Machine Learning, Statistics, Engineering or equivalent professional experience.
• 10+ years of related industry experience.
• Experience designing and deploying agentic or multi-step AI systems (e.g., ReAct, tool-calling agents, multi-agent pipelines).
• Strong proficiency in Python and ML frameworks; experience with LLM APIs and orchestration libraries.
• 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 evaluation frameworks for ML systems, including offline benchmarking and production monitoring.

Responsibilities

• Design, build, and evaluate multi-step agentic AI systems with autonomous agents.
• Research and implement techniques in agentic architectures (ReAct, reflection loops, chain-of-thought).
• Develop and maintain agent orchestration frameworks for task decomposition and recovery.
• Integrate LLMs with external tools, APIs, databases, and code execution environments.
• Define evaluation frameworks measuring reliability, latency, cost, and safety across benchmarks.
• Lead collaboration with product, engineering, and research teams to translate requirements into designs.
• Mentor senior ML engineers and scientists on agentic design patterns and experimentation methodology.

Skills

Python

PyTorch

TensorFlow

JAX

LLM APIs

LangChain

LlamaIndex

Prompt engineering

Production deployment

Mentoring

Education

BS in CS/ML/Statistics/Engineering

PhD or MS (preferred)

Tools

APIs integration

Job description

Expedia Group seeks an experienced engineering leader to design and deploy agentic, multi-step AI systems that can plan, use tools, and collaborate across sub‑agents. You will explore ReAct, reflection loops, and prompt engineering while coordinating with product and research teams in Seattle.

The role requires 10+ years in ML, strong Python skills, and a track record of production ML deployments. Competitive pay and full benefits accompany a hybrid work model in the Seattle area.