Sr. Software Dev Engineer, Alexa LLM Inference, Capacity, & Efficiency

Are you passionate about building and operating the world's largest real-time LLM inference systems? Are you a technical leader who thrives in high-ambiguity environments and wants to drive architectural decisions that impact millions of Alexa customers daily? If so, the Alexa LLM Inference, Capacity, & Efficiency (ALICE) team is looking for a Senior Software Development Engineer to join our new India team and own critical components of Alexa's LLM inference infrastructure. Alexa is shaping the future of AI voice-based personal assistants. At ALICE, we are passionate about infrastructure efficiency, cost optimization, and capacity management to enable amazing customer experiences at scale. You will be a founding technical leader of our India presence, setting the bar for engineering excellence and driving high-impact work on one of Amazon's most critical AI services. Key job responsibilities - Serve as a technical leader for the ALICE India team, driving architecture decisions for the AlexaLLMInferenceService (LLMI) and related ALICE portfolio services - Design and implement scalable, high-availability systems for LLM inference serving, including multi-node distributed inference and multi-tenancy capabilities - Lead technical design reviews, set coding standards, and mentor junior SDEs on the team - Make technical trade-offs between short-term team needs and long-term business needs, with a focus on performance, cost, and reliability - Collaborate with ALICE teams in Seattle and partner teams across Alexa and AGI on cross-cutting infrastructure programs - Drive operational excellence for Tier-1 production services, including on-call ownership, incident response, and continuous improvement - Influence the broader ALICE software architecture and contribute to org-wide technical strategy A day in the life As a Senior SDE, you will be part of the technical leadership for the India team, owning architecture decisions for LLMI components and contributing to ALICE's broader portfolio of infrastructure optimization products.