Senior Software Development Engineer - Genai Platform

Expedia Expedia · Hospitality · IL

Expedia Group is seeking a Senior Software Development Engineer to join their GenAI Platform team. This role will focus on building and operating a shared generative AI platform, including tooling, services, and guardrails, to enable product and ML teams to safely experiment with, deploy, and scale GenAI-powered experiences. The engineer will lead the design, delivery, and evolution of scalable GenAI services and multi-agent infrastructure, focusing on system design, API design, data modeling, and integrating with LLM providers and vector stores. The role also involves contributing to GenAI platform guardrails and safety features, partnering with cross-functional teams, and creating technical documentation.

What you'd actually do

  1. Design, build, and operate Python/FastAPI backend services and APIs that power GenAI Platform capabilities such as RAG managers, data planes, and vector store services, with strong focus on system design, API design, and data modeling.
  2. Implement clean, maintainable, and well-tested code using modern engineering practices including code reviews, CI/CD pipelines, automated testing, monitoring, alerting, and participating in on-call rotations where applicable.
  3. Integrate platform services with internal and external LLM providers, Elasticsearch-based vector stores, and Aurora PostgreSQL as part of scalable, reliable RAG and retrieval workflows across multiple domains.
  4. Contribute to and evolve GenAI platform guardrails and safety features (authentication, API key management, workload-to-workload authentication, evaluation and observability hooks) so AI-enabled applications are secure, responsible, observable, cost-aware, and safely integrate and operate AI/ML‑enabled solutions that improve outcomes.
  5. Partner closely with staff and principal engineers, product managers, applied scientists, and other engineering teams to refine requirements, shape platform architecture (including multi-tenant vector stores and workflow integrations), and deliver incremental, production-ready value.

Skills

Required

  • Python
  • FastAPI
  • backend services
  • APIs
  • system design
  • API design
  • data modeling
  • public or hybrid cloud environments
  • AWS
  • data store technology (relational, NoSQL, or search)
  • Aurora PostgreSQL
  • Elasticsearch
  • LLM-powered capabilities
  • embeddings
  • RAG patterns

Nice to have

  • performance tuning
  • resilience patterns
  • high-traffic or multi-tenant services
  • RAG
  • vector store tooling
  • LangChain
  • LlamaIndex
  • LangGraph
  • evaluation frameworks
  • observability frameworks
  • LangSmith
  • Langfuse
  • prompt and retrieval design
  • Elasticsearch vector search
  • internal platforms
  • SDKs
  • shared services
  • workflow and agent orchestration
  • n8n
  • Flowise
  • multi-tool or multi-agent GenAI applications

What the JD emphasized

  • end-to-end ownership
  • building and operating backend APIs at scale
  • safely integrating and operating AI/ML‑enabled solutions
  • safely experiment with, deploy, and scale GenAI-powered experiences

Other signals

  • build and operate shared generative AI platform
  • tooling, services, and guardrails
  • safely experiment with, deploy, and scale GenAI-powered experiences
  • scalable GenAI services and multi-agent infrastructure
  • codifying guardrails and best practices
  • partnering closely with product and domain engineering teams
  • accelerate how internal teams build, integrate, and safely operate AI-enabled experiences