Senior SDE, Luna Gen AI

Amazon•Seattle, WA

48d

About The Position

We are seeking a Senior Software Development Engineer to join our Gen AI & Strategic Initiatives team that spans our Amazon Luna business. You will be a critical early member as we drive towards two key areas of AI integration 1) to create new types of Gen AI native games and gameplay experiences and 2) to enhance productivity of our internal team through the adoption of best practices and tools as well as the creation of agents. As a Gen AI Technical Leader, you'll architect next-generation tools that will drive the adoption of transformative AI solutions for both external game developers as well as our internal engineering teams. You will be a hands-on builder who designs, develops, and operates the platform infrastructure to support both proprietary and third party models. Your expertise in distributed systems and API design will enable you to build resilient, performant solutions that abstract the complexity of multiple AI providers behind unified interfaces. In addition to creative primitives, you will also lead the work to implement agents for workstreams across Engineering, Martech, business intelligence and more. We're looking for a Senior Software Engineer with a developer-focused, customer-obsessed mindset, strong ownership mentality, and deep expertise in building production systems at scale. This is an exciting opportunity to excel in a dynamic, scrappy environment where you’ll shape the future of gaming with AI.

Requirements

Bachelor's degree in computer science or equivalent
5+ years of non-internship professional software development experience
5+ years of programming with at least one software programming language experience
5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
Experience as a mentor, tech lead or leading an engineering team
Experience with AWS or cloud technologies

Nice To Haves

5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
Experience building large-scale machine learning and AI solutions at Internet scale
Experience in software development
Master's degree in Computer Science or related technical field
6+ years of game industry experience

Responsibilities

Drive platform architecture decisions - Work closely with GenAI leadership to understand model requirements and translate them into scalable platform capabilities; contribute to technical design reviews and architectural decisions
Build and operate high-scale API infrastructure - Design, develop, and maintain secure, scalable APIs using AWS API Gateway that provide unified access to multiple AI service providers including Bedrock, SageMaker, and vendors like ElevenLabs; implement robust authentication, authorization, and credential management systems
Launch cross-functional agents - Identify key use cases to increase productivity and partner with domain experts to create agentic workflows and systems.
Evaluate & optimize performance - Design caching strategies, implement request optimization, and build cost monitoring systems to deliver low-latency responses while managing expenses across multiple AI service providers
Support developer experience and adoption - Create developer tools, SDKs, documentation, technical demos and sample code to accelerate adoption; provide technical support and guidance to internal and external developers integrating with the platform
Implement comprehensive observability and monitoring - Build end-to-end logging, metrics, alerting, and dashboards to ensure operational excellence; define and monitor SLAs, implement automated response systems, and create runbooks for incident management
Design throttling and resource management systems - Implement sophisticated rate limiting, quota management, and traffic shaping to ensure fair usage across gaming workloads while protecting underlying AI services from overload
Ensure enterprise-grade security and compliance - Implement secure credential injection, token management, encryption in transit and at rest, and audit logging to meet gaming industry security standards and compliance requirements
Drive operational excellence and reliability - Build automated deployment pipelines, implement chaos engineering practices, conduct post-incident reviews, and continuously improve system resilience and availability