Agentic AI Scientist II — Multi-Agent Systems Leader

Expedia Group; Austin (TX); On-site; USD 112,000 - 179,000; Full time

Benefits offered by this job

Medical, dental, and vision coverage

Paid time off

Employee Assistance Program

Welfare and travel reimbursement

Travel discounts

IATAN membership

Job summary

Expedia Group is seeking a highly skilled AI researcher/software engineer to design, implement, and operationalize multi-step, agentic AI systems that can plan, use tools, and collaborate across sub-agents. You will advance architectures like ReAct, chain-of-thought prompting, and tool-augmented reasoning while ensuring robust evaluation and safe deployment.

You’ll work with product, engineering, and research teams to translate business needs into scalable agentic solutions, manage risks, and

Qualifications

• PhD, MS, or BS in Computer Science, ML, Statistics, Engineering, or related field; or equivalent professional experience
• 2 years of related industry experience
• Experience designing and deploying agentic or multi-step AI systems (e.g., ReAct, tool-calling agents) in production
• Proficiency in Python and ML frameworks; experience with LLM APIs and orchestration libraries
• Experience integrating LLMs with external tools, APIs, and structured data sources
• 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, 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

Skills

Agentic AI design

Python

ML frameworks (PyTorch, TensorFlow, JX

LLM APIs

LangChain / LlamaIndex

Prompt engineering

Evaluation frameworks for ML systems

Education

PhD/MS/BS in CS/ML/Engineering or related field

Equivalent professional experience

Tools

LangChain

LlamaIndex

ReAct

APIs and tools integration

Job description

Expedia Group is seeking a highly skilled AI researcher/software engineer to design, implement, and operationalize multi-step, agentic AI systems that can plan, use tools, and collaborate across sub-agents. You will advance architectures like ReAct, chain-of-thought prompting, and tool-augmented reasoning while ensuring robust evaluation and safe deployment.

You’ll work with product, engineering, and research teams to translate business needs into scalable agentic solutions, manage risks, and