Join our dynamic AI Runtime team and play a pivotal role in shaping the future of Alexa+. We are seeking an experienced Software Development Engineer passionate about building and scaling cutting-edge AI infrastructure. Your contributions will involve designing and implementing Tier-1 distributed systems crucial for orchestrating expert agent executions, managing LLM inference pipelines, and ensuring seamless, low-latency delivery across Alexa-enabled devices worldwide. This is a high-impact opportunity where your work directly influences the daily experience of millions of customers.

Your responsibilities will include designing, building, and operating large-scale distributed services that power Alexa+ Expert executions. You'll develop and optimize LLM orchestration pipelines, encompassing model serving, prompt routing, and inference enhancements. Furthermore, you will construct multi-agent coordination systems for efficient request routing and own the operational excellence of Tier-1 services, striving for 99.99%+ availability. Collaboration with applied scientists and ML engineers to integrate AI capabilities and driving architectural decisions for performance, reliability, and cost-efficiency are also key. Mentoring teammates and elevating engineering standards through reviews and technical leadership are expected.

We are looking for candidates with a Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field, coupled with 3+ years of professional software development experience (non-internship). A minimum of 2 years in designing or architecting new and existing systems, with a focus on reliability and scaling, is essential. Proficiency in at least one programming language is required. Preferred qualifications include 3+ years of experience across the full software development lifecycle and familiarity with system design involving AI components, evaluating latency, cost, reliability, and accuracy.