25 days ago
Responsibilities
- Drive end-to-end system design, including low-level designs, API contracts, and data modeling.
- Build, release, and operate scalable GenAI services, backend APIs, and multi-agent infrastructure.
- Create reusable, extensible, self-service platform capabilities and support adoption by product and domain engineering teams.
- Define metrics for reliability, performance, adoption, and operating cost.
- Establish grading standards for AI agents, MCP servers, and skills covering quality, safety, reliability, and production readiness.
- Design intelligent routing patterns, open-weight model deployments, and fine-tuning pipelines with the LLM Inference team.
- Ensure engineering quality through testing, security, observability, and operational readiness.
- Collaborate with distributed teams and cross-functional partners on technical decisions, dependencies, and platform adoption.
Requirements
- Bachelor’s degree in Computer Science or a related technical field, or equivalent related professional experience.
- 8+ years of relevant professional experience building and operating backend services and APIs with end-to-end ownership.
- Proficiency in Python and production-grade web service development using FastAPI or similar frameworks such as Flask or Django.
- Strong understanding of system design, API design, and data modeling.
- Experience operating backend APIs in public or hybrid cloud environments, preferably AWS.
- Experience with at least one data store, such as Aurora PostgreSQL or Elasticsearch.
- Familiarity with AI-driven systems, LLM-powered capabilities, embeddings, RAG patterns, or the ability to quickly learn GenAI platform tools.
- Preferred: experience operating Python backend APIs at scale, including performance tuning, resilience patterns, and multi-tenant services.
- Preferred: hands-on experience with RAG, vector stores, LangChain, LlamaIndex, LangGraph, LangSmith, or Langfuse.
- Preferred: experience integrating LLM systems, prompt and retrieval design, embeddings management, Elasticsearch vector search, Aurora PostgreSQL schemas, authentication, quotas, and evaluation hooks.
- Preferred: experience building internal platforms, SDKs, or shared services adopted by multiple product teams.
- Preferred: experience with workflow and agent orchestration tools such as n8n or Flowise and AI platform safety practices.
Benefits
- Medical, dental, and vision coverage.
- Paid time off and an Employee Assistance Program.
- Wellness and travel reimbursement.
- Travel discounts and International Airlines Travel Agent Network membership.
- The position is located in Chicago; compensation and starting pay vary based on location, budget, and qualifications.
Tech Stack
Categories
About Expedia
Expedia Group builds a global online travel marketplace where consumers book flights, hotels, vacation rentals, cars, and activities, and partners distribute and market inventory across its platform. It monetizes through commissions, merchant/agency models, and advertising via brands including Expedia, Hotels.com, and Vrbo. Founded in 1996 and headquartered in Seattle, the public company (NASDAQ: EXPE) serves travelers and partners in more than 70 countries with B2C, B2B, and ad tech offerings.