Software Development Manager, Alexa AI Logistics for Infrastructure, Cost, & Efficiency

Description

• Are you passionate about leading engineering teams that power the world's largest real-time AI inference systems? Are you customer-obsessed and excited about building the foundational infrastructure that

Description

• Are you passionate about leading engineering teams that power the world's largest real-time AI inference systems? Are you customer-obsessed and excited about building the foundational infrastructure that enables the next generation of Alexa experiences? If so, the Alexa AI Logistics for Infrastructure, Cost, and Efficiency (ALICE) team is looking for a Software Development Manager to lead critical work at the intersection of AI infrastructure, inference service engineering, and cloud-scale systems. Alexa is shaping the future of AI voice-based personal assistants, and we need your help to own and lead large-scale technical programs that power the next generation of Alexa experiences. Alexa is the Amazon cloud AI service and brain that powers Echo and Alexa-enabled devices worldwide. We believe voice is the most natural user interface for interacting with technology across many domains — we are inventing the future. At ALICE, we are passionate about continuously improving infrastructure efficiency, cost optimization, and capacity management to enable amazing customer experiences at scale. Key job responsibilities You will lead a team of Software Development Engineers responsible for critical inference service components within ALICE's portfolio, with a primary focus on building and operating a centralized inference management service that sits at the heart of Alexa's AI infrastructure. Your team will be responsible for: - Owning and operating a centralized inference service that manages model access, capacity utilization, and intelligent traffic prioritization and throttling at massive scale - Ensuring inference services meet Alexa's stringent latency and throughput requirements, with comprehensive observability and monitoring - Building solutions that maximize the efficiency of GPU and compute resources, including scheduling systems that optimize workload execution across real-time and offline inference traffic - Driving infrastructure expansion into new AWS regions to support Alexa's international growth - Collaborating with teams across Alexa, AGI, and AWS to align inference service capabilities with evolving product and infrastructure needs You must be able to thrive and succeed in an entrepreneurial environment, and not be hindered by ambiguity or competing priorities. This means you are not only able to develop and drive high-level strategic initiatives, but can also roll up your sleeves, dig in and get the job done. You will anticipate bottlenecks, provide escalation management, anticipate and make tradeoffs, and balance business needs versus technical constraints. Maturity, high judgment, negotiation skills, ability to influence, analytical talent, and leadership are essential to success in this role.

Basic Qualifications

• - 3+ years of engineering team management experience - 7+ years of working directly within engineering teams experience - 3+ years of designing or architecting (design patterns, reliability and scaling) of new and existing systems experience - 8+ years of leading the definition and development of multi tier web services experience - Knowledge of engineering practices and patterns for the full software/hardware/networks development life cycle, including coding standards, code reviews, source control management, build processes, testing, certification, and livesite operations - Experience partnering with product or program management teams

Preferred Qualifications