Join our dynamic team as a Software Development Engineer focused on AI Runtime infrastructure for Alexa+. This is a key role where you will architect and implement critical distributed systems essential for expert agent execution, LLM inference pipelines, and low-latency global delivery across Alexa devices. Your contributions will directly influence the daily experience of millions of users.

This high-impact position offers the opportunity to shape the future of AI-driven interactions. Be part of a team building the foundational elements that make Alexa+ feel magical.

Design, develop, and maintain large-scale distributed services powering Alexa+ Expert executions. Optimize LLM orchestration pipelines, including model serving, prompt routing, and inference efficiency. Build sophisticated multi-agent coordination systems for minimal latency request routing. Ensure operational excellence and high availability for Tier-1 services. Collaborate closely with applied scientists and ML engineers to integrate cutting-edge AI capabilities into production. Drive architectural decisions balancing performance, reliability, and cost. Mentor team members and elevate engineering standards through comprehensive code and design reviews.

A minimum of 3 years of professional software development experience (excluding internships) is required. Additionally, at least 2 years of experience in designing or architecting new and existing systems, focusing on design patterns, reliability, and scaling, is essential. A Bachelor's degree or its foreign equivalent in Computer Science, Engineering, Mathematics, or a related field is necessary. Proficiency in at least one programming language is a must.

Preferred qualifications include 3+ years of experience across the full software development life cycle, encompassing coding standards, code reviews, source control, build processes, testing, and operations. A Bachelor's degree in Computer Science or equivalent is beneficial. Experience with system design incorporating AI components, evaluating latency, cost, reliability, and accuracy, is highly valued.