We are looking for a Software Development Engineer to help build and scale the infrastructure powering Amazon’s next-generation agentic advertiser guidance framework. In this role, you will design and implement core components of the agent execution engine, evaluation pipelines, and model tuning infrastructure that enable agents to reason, plan, and act across complex advertiser workflows. You will work closely with senior engineers and applied scientists to translate research prototypes into robust, high-performance production systems. You will need to dive deep into new technologies—such as LLM deployment frameworks, reinforcement learning infrastructure, and multi-step reasoning orchestration—and quickly apply them to solve real customer problems. You will own well-defined but often ambiguous technical problems, ensuring your solutions are scalable, reliable, and directly contribute to advertiser-facing products. This role is highly impactful: your contributions will form the backbone of the systems that deliver personalized, context-aware guidance to millions of advertisers. You will collaborate across science, product, and platform teams, and your work will focus on building resilient, observable, and maintainable systems that accelerate innovation in agent-based AI.