Sr. Software Dev Engineer, Alexa LLM Inference, Capacity, & Efficiency
Core
Founding technical leader for the India team building and operating real-time LLM inference systems for Alexa, focusing on infrastructure efficiency, cost optimization, and capacity management.
Role type
Senior IC software development engineer (LLM inference infrastructure)
Builds
Scalable, high-availability systems for LLM inference serving, including multi-node distributed inference and multi-tenancy capabilities
Domain
AI/ML infrastructure, cloud computing, real-time systems
Deliverable
production ML models
Required skills
Java, C++, C#, object-oriented design, system architecture, design patterns, reliability engineering, scaling, on-call ownership, incident response
Preferred skills
Full software development life cycle management, coding standards, code reviews, source control management, build processes, testing
Technologies
Java, C++, C#
Responsibilities
Drive architecture decisions for LLMI and related services, design and implement scalable distributed inference systems, lead technical design reviews and mentor junior engineers, make technical trade-offs for performance and cost, collaborate with Seattle and partner teams, own Tier-1 production service operations
Seniority
Senior, hands-on IC with leadership responsibilities