Software Development Engineer III - AI

Expedia•Austin, TX

2d•$146,000 - $233,500•Hybrid

About The Position

Expedia Global Payments (EGP) is seeking experienced engineering talent to contribute to the development of its payment platform. This role involves seamlessly rolling out new payment methods, continuously improving operational excellence, and enhancing engineering practices. The team manages a dynamic set of services that facilitate global payments for customers, supporting Expedia Group's brands, suppliers, and corporate needs. The platform processes over $100 billion in payments annually across 55+ currencies and 155+ countries, utilizing a diverse range of payment options. This position offers significant technical challenges and the potential for substantial business impact. Technology and innovation are central to the organization's mission, focusing on solutions that reduce payment costs and improve performance, scalability, availability, and resiliency. The role also involves providing functional support to platform services and adapting to new payment solutions and capabilities. This specific position emphasizes implementing innovative software solutions for large-scale e-commerce payment systems, acting as a role model, and mentoring fellow engineers. It provides opportunities to expand skills in building highly scalable solutions, influence others, and elevate the team's overall engineering excellence. Additionally, the role offers the chance to influence decisions across Expedia Group's technology ecosystem by serving as a key domain guide and contributing to the selection of new senior-level hires.

Requirements

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.

Nice To Haves

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.

Responsibilities

Design and deliver real-time, AI-powered fraud and abuse defenses on a global scale.
Build and operate cloud-native decisioning and automated remediation systems.
Help simplify the platform.
Collaborate with cross-functional teams to achieve measurable outcomes.
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 built.
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 owned, 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.