Senior Software Development Engineer (genai, Agentic Ai)

Expedia Expedia · Hospitality · Seattle, WA

Senior Software Development Engineer focused on AI, specifically Generative and Agentic AI for fraud and risk detection at Expedia Group. The role involves leading architecture, design, and delivery of real-time AI-powered systems, integrating LLMs and multi-agent applications, and operating ML in production. Experience with RAG, vector databases, and LLM providers is required.

What you'd actually do

  1. Own technical architecture and lead design and delivery of AI-driven solutions for automated risk decisioning and remediation.
  2. Incorporate and integrate Generative and Agentic AI into fraud detection workflows, simplifying and modernizing the platform while reducing time to detect and mitigate attacks.
  3. Benchmark various vendor, open source and in-house solutions for performance, cost and risk posture.
  4. Build, deploy, and operate ML in production; partner closely with Data Science/ML Scientists on features, experimentation, and monitoring.
  5. Establish clear SLOs, observability, and safety/rollback mechanisms; ensure security, privacy, and compliance are built in.

Skills

Required

  • Java/Scala/Go/Python
  • LLM and multi-agent applications
  • LangChain, LangGraph, Langfuse or equivalent
  • RAG-based architecture
  • LlamaIndex, Pinecone or equivalent
  • OpenAI, Gemini, Anthropic
  • Production ML experience
  • Distributed cloud-native engineering at scale (AWS, GCP, or Azure)
  • Microservices
  • API-driven design
  • SQL/NoSQL databases
  • Data streaming/processing (Kafka, Flink, Spark)

Nice to have

  • fraud and risk systems in production
  • Graph/sequence modeling or entity resolution at scale
  • device and behavioral signals
  • automation and platform simplification

What the JD emphasized

  • 9+ years of software engineering, including significant experience developing, deploying and operating ML/AI driven solutions in production.
  • Demonstrable experience building, monitoring and debugging LLM and multi-agent applications, with frameworks and platforms such as LangChain, LangGraph, Langfuse, or equivalent.
  • RAG-based architecture experience, including data orchestration frameworks such as LlamaIndex, vector databases such as Pinecone, or equivalent.
  • Production ML experience (supervised/anomaly detection, feature pipelines, online inference, monitoring/retraining); ability to ship with Data Science/ML Science partners.

Other signals

  • AI-powered fraud and abuse defenses
  • Generative and Agentic AI into fraud detection workflows
  • Build, deploy, and operate ML in production
  • LLM and multi-agent applications
  • RAG-based architecture