Senior Software Development Engineer - GenAI

Expedia Group•Chicago, IL

6d•$171,500 - $240,000

About The Position

The Senior Software Developer role is part of Expedia Group’s GenAI Platform team, which builds and operates shared generative AI tooling, services, and guardrails. The role leads the design, delivery, and evolution of scalable GenAI services and multi-agent infrastructure that enable secure and observable GenAI capabilities across Expedia Group. It shapes platform architecture, establishes guardrails and best practices, and partners with product and domain engineering teams to help them build and operate AI-enabled experiences for travelers and partners at global scale. The position owns work from system design through implementation, release, and production operations. It develops reusable, extensible, self-service platform capabilities and works across distributed teams, partnering with the AI Registry team on AI asset grading standards and with the LLM Inference team on routing, open-weight model deployments, and fine-tuning pipelines.

Requirements

Bachelor’s degree in Computer Science or a related technical field, or equivalent related professional experience.
8+ years of relevant professional experience, including building and operating backend services and APIs with end-to-end ownership from design through deployment and ongoing operational support.
Proficiency in Python and experience developing production-grade web services using FastAPI or similar modern frameworks, with a solid understanding of system design, API design, and data modeling.
Experience building and running backend APIs in public or hybrid cloud environments, hands-on exposure to core cloud services (AWS preferred), and experience with at least one data store technology (relational, NoSQL, or search), such as Aurora PostgreSQL or Elasticsearch.
Familiarity with AI-driven systems, tools, or workflows and applying AI/ML concepts to real-world products, including exposure to LLM-powered capabilities, embeddings, or RAG patterns, or demonstrated ability to ramp up quickly using internal GenAI Platform tools and documentation.

Nice To Haves

Deep experience building and operating Python-based backend APIs at scale on AWS or similar cloud providers, including performance tuning, resilience patterns, and advanced API and data modeling for high-traffic or multi-tenant services.
Hands-on experience with RAG and vector store tooling such as LangChain, LlamaIndex, or LangGraph, and evaluation or observability frameworks such as LangSmith or Langfuse, including safe integration and operation of AI/ML-enabled solutions.
Experience integrating and optimizing LLM-powered systems end to end, including prompt and retrieval design, embeddings management, Elasticsearch vector search, Aurora PostgreSQL schemas, and platform-level guardrails such as authentication, quotas, and evaluation hooks.
Background building internal platforms, SDKs, or shared services adopted by multiple product teams, including clear documentation, paved-road patterns, and collaboration with product management, applied science, and engineering.
Experience designing or implementing workflow and agent orchestration-based solutions, for example using n8n, Flowise, or similar tools, to build multi-tool or multi-agent GenAI applications, and familiarity with AI-driven platform architectures and safety-by-design practices.

Responsibilities

Drive end-to-end system design, including low-level design, API contracts, and data modeling, aligned with Expedia’s architectural standards, engineering practices, and long-term technical vision.
Collaborate across geographically distributed teams, clarify technical decisions, ownership, and dependencies, and work with use-case teams to understand requirements and support platform adoption.
Own delivery from design through implementation, release, and production operations, ensuring quality through testing, security, observability, and operational readiness.
Define and track reliability, performance, adoption, and operating-cost metrics.
Build reusable, extensible, self-service platform capabilities, balancing consistent interfaces and sensible defaults with workload-specific flexibility.
Partner with the AI Registry team to define and implement grading standards for AI assets, including AI agents, MCP servers, and skills, with criteria for quality, safety, reliability, and production readiness.
Work with the LLM Inference team on intelligent routing patterns, open-weight model deployments, and fine-tuning pipelines, balancing model quality, latency, reliability, and cost.