Amazon Senior Software Development Engineer SPB Advertiser Guidance 

United States, California, Palo Alto 

41032807

We are looking for a Senior Software Development Engineer who will own the infrastructure, platform, and production systems that underpin our agentic advertiser guidance framework. In this role, you will lead the design, build, and scaling of core services such as tool orchestration, agent execution engine, evaluation pipelines, model serving/tuning infrastructure, and monitoring systems. You will work closely with applied scientists and engineers to translate prototype agent capabilities into robust, scalable production systems. You will need to rapidly learn and apply new techniques in agent deployment, model tuning, reinforcement learning infrastructure, multi-step reasoning orchestration, and system optimization. You will build APIs, pipelines, and frameworks that allow agents to reason, plan, and act reliably at scale, ensuring low latency, high throughput, resilience, fault tolerance, versioning, and safety guardrails. A critical aspect of this role is being customer-obsessed: you will work backwards from advertiser needs to ensure that infrastructure decisions enable real customer-facing experiences. You will also partner with cross-functional teams—science, product, operations—to continuously iterate the agentic architecture, evaluation metrics, and tuning loops. This is a high-impact role where you balance deep technical craftsmanship with product sensibility, setting standards, influencing architecture, and owning end-to-end delivery of agentic capabilities.Key job responsibilities
- Lead engineering strategy and roadmap for Sponsored Products Agentic Advertiser Guidance
- Design and implement scalable architecture to host agent orchestration, tool invocation, state management, and feedback loops.
- Build scalable, reusable data and tool registry- Integrate and manage tuning pipelines (e.g. hyperparameter tuning, RL fine-tuning, preference optimization), and provide abstraction layers for scientists to plug in models.
- Implement observability, logging, metrics, alerting, tracing, and drift detection for agent behaviors and model performance.- Rapidly prototype and evaluate new system designs or algorithmic patterns (e.g. streaming inference, memory caching, chaining of reasoning modules, tool embeddings).

- 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

- 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Bachelor's degree in computer science or equivalent