Software Development Engineer III - AI

Introduction to the Team 

Expedia Global Payments (EGP) is looking for top engineering talent to help drive the development of our payment platform, seamlessly roll out new payment methods, and continuously improve on our operational excellence and engineering practices. We offer a highly dynamic set of services that enable customers worldwide to pay for travel in a variety of ways. We build, operate, and improve payment services for Expedia Group's brands, our suppliers (hoteliers, airlines, vacation rental owners/agencies, etc.), and our corporate needs. We do this accurately and at scale, processing over $100 billion payments in 55+ currencies in over 155 countries every year, and across a diverse set of payment options! This opportunity presents great technical challenges and offers the potential to have a tremendous business impact. 
 
Technology and innovation are at the heart of our organization. We provide solutions that reduce the cost of payments and improve performance, scalability, availability, and resiliency. We also provide an abundance of functional support to services in our platform, and the needs are ever-growing, as we adapt to new payment solutions and capabilities. 
 
This position focuses not only on implementing innovative software solutions for e-commerce payment systems at scale but also on being a role model and mentor to your fellow engineers. You will get to expand your skills in building highly scalable solutions while influencing others and raising the bar on the overall level of excellence within the team. You will also get the opportunity to influence decisions across the technology ecosystem within Expedia Group by being a key domain guide. Additionally, your input will be critical to the selection of new senior-level hires on the team. 

Role Summary 

Design and deliver real-time, AI-powered fraud and abuse defenses on a global scale. As a Software Development Engineer III, you will build and operate cloud-native decisioning and automated remediation systems, help simplify our platform, and collaborate with cross-functional teams to achieve measurable outcomes. 
 
In this role you will: 

• Contribute to the design and implementation of low-latency risk decisioning (signals + rules + models) and automated remediation, owning the quality and reliability of the services and components you build. 

• Apply AI-assisted SDLC practices end to end: AI-accelerated design and code generation, prompt and context management for coding agents, human-in-the-loop review of AI-generated code, automated test generation, and CI/CD guardrails. 

• Build, deploy, and operate agentic workflows and multi-agent systems — decomposing tasks, orchestrating tools and function calls, managing memory, and embedding human-in-the-loop controls — to automate and reimagine manual operational processes, not just augment them. 

• Help simplify and modernize the platform (streaming/data pipelines, microservices, CI/CD, configuration-driven controls) so that teams can iterate quickly and safely. 

• Implement and maintain SLOs, observability, and safety/rollback mechanisms for the services you own, ensuring security, privacy, and compliance requirements are met by design. 

• Participate in evaluating vendors and in-house solutions for performance, cost, and risk posture, contributing data and implementation perspectives into the decision process. 

• Collaborate closely with engineering, product, operations, security, and compliance teams to deliver outcomes, sharing knowledge with peers and supporting a high bar for engineering excellence. 

• Mentor other engineers and champion the use of AI within the organization 

Minimum Qualifications  

• Bachelor’s degree in Computer Science or a related technical field; or equivalent related professional experience. 

• 5+ years of software engineering, with significant experience building and operating high-scale production backend services, including shipping Gen AI and agentic systems to production. 

• Hands-on proficiency in at least one modern programming language and core software engineering practices, including system design (LLD), API design, and data modeling for AI-enabled services. 

• Familiarity with distributed cloud-native engineering at scale (AWS, GCP, or Azure), microservices, API-driven design, SQL/NoSQL databases, and data streaming/processing (Kafka, Flink, Spark). 

• Hands-on experience using AI coding assistants and agents (e.g., Claude Code, Cursor, GitHub Copilot, or equivalent) to ship production software faster — applying AI-assisted SDLC practices across design, implementation, reviews, and test generation, with strong prompt/context management and human-in-the-loop review of AI-generated code. 

• 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. 

• Exposure to various LLM providers such as OpenAI, Gemini, and Anthropic. 

Preferred Qualifications: 

• Track record automating and reimagining manual operational processes with agentic systems, reducing manual operations through automation and platform simplification. 

• Experience building and integrating applications with AI/ML solutions or LLM models, including model API consumption, RAG patterns, agentic orchestration, and connecting AI-driven outputs to scalable backend services with observability and cost-awareness. 

• Graph/sequence modeling or entity resolution at scale; device and behavioral signals. 

• Experience with cloud cost/performance tuning and capacity planning. 

• Marketplace, travel, or e-commerce experience. 

Please note that this role is only available in Austin, TX, in alignment with our flexible work model, which requires employees to be in-office at least three days a week. We are unable to offer relocation assistance for this role.