SDE-III SP Agentic Interfaces, Spectrum — Selling Partner Developer Experience

The Spectrum organization owns critical platform infrastructure that hundreds of thousands of third-party Solution Providers depend on to build applications powering millions of Amazon sellers. Our services process billions of API calls, manage complex permission and authorization models across global marketplaces, and serve as the front door for every Solution Provider building on Amazon's commerce platform. We're looking for a senior technical leader to own the architecture and drive delivery of agentic AI systems within our platform. This is a role for someone who sees the full picture — you'll take ambiguous business problems, define the technology strategy, and lead your team through delivery of production AI agent systems that fundamentally reshape how Solution Providers interact with our platform. You'll proactively identify architecture deficiencies, simplify complex systems, and make trade-offs between short-term business needs and long-term technology investments. Your influence will extend beyond your team as you drive alignment with partner teams on coherent architectural strategies. Key job responsibilities * Own team-level architecture for agentic AI systems — define how AI agents interact with your team's platform services (authorization, permissions, notifications, identity, and developer workflows). Proactively fix architecture deficiencies and simplify existing systems. * Lead large, complex AI initiatives end-to-end — decompose ambiguous problem statements into parallel workstreams, assign components to team members, and reassemble into cohesive launches. You know when to build new and when to extend existing solutions. * Design AI agent frameworks and platform architecture including tool-use orchestration, context retrieval (RAG over developer docs, API specs, and account data), guardrails, memory systems, and evaluation pipelines — making trade-offs between extensibility, performance, and operational complexity. * Leverage AI-DLC to build world-class experiences for Sellers and Solution Providers to discover and leverage agentic capabilities across their interface of choice. * Build intelligent automation for high-volume operational workflows: vetting tools with human-in-the-loop, agentic ticket triage and resolution, proactive Solution Provider health monitoring, automated onboarding guidance, and self-service diagnostic tools. * Define metrics, evaluation frameworks, and guardrails for AI agent quality — accuracy, resolution rate, latency, safety, drift detection — and build the instrumentation to measure and improve them in production. Drive A/B testing of model outputs and establish feedback loops. * Drive engineering excellence across the team — set standards for code quality, operational excellence, security, and testability. Resolve root causes of endemic problems including areas where your team's systems bottleneck other teams' innovation. * Operate at Amazon scale — own Tier-1 services across multiple regions. Make principled trade-offs between short-term operational needs and long-term technology investments. Maintain the high availability bar expected of platform infrastructure. * Influence technical direction beyond your team — lead architecture reviews, drive design alignment with partner teams across the Spectrum organization, and negotiate technical decisions where systems intersect. Build consensus across discordant views. * Actively mentor and develop team members — coach SDEs on design approaches, lead technical assessments, raise the engineering bar through code reviews, and ensure the team is stronger because of your presence but does not require it to be successful. A day in the life The average day is focused on delivering upon our prioritized product features and collaborating with members of the team on planning and designing future features. We gather on a daily Scrum to support each other in our work and help overcome blockers as a team.

The