About Sponsored Products and Brands

The Sponsored Products and Brands team at Amazon Ads is re-imagining the advertising landscape through cutting-edge generative AI technologies, revolutionizing how millions of customers discover products and engage with brands across Amazon.com and beyond. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle from ad creation and optimization to performance analysis and customer insights. We are a passionate group of innovators dedicated to developing responsible and intelligent AI technologies that balance the needs of advertisers, enhance the shopping experience, and strengthen the marketplace. If you're energized by solving complex challenges and pushing the boundaries of what's possible with AI, join us in shaping the future of advertising.

About our team

SPB Agent team's vision is to build a highly personalized and context-aware agentic advertiser guidance system that seamlessly integrates Large Language Models (LLMs) with sophisticated tooling, operating across both conversational and traditional ad console experiences. We scale from natural language queries to proactive, intelligent guidance delivery based on deep advertiser understanding. Through strategic partnerships across Ad Console, Sales, and Marketing teams, we identify high-impact opportunities spanning from strategic product guidance to granular optimization and deliver them through personalized, scalable experiences grounded in state-of-the-art agent architectures, reasoning frameworks, sophisticated tool integration, and model customization approaches including fine-tuning, MCP, and preference optimization. This presents an exceptional opportunity to shape the future of e-commerce advertising through advanced AI technology at unprecedented scale, creating solutions that directly impact millions of advertisers.

Curious about our advertising solutions? Discover more about Sponsored Products and Sponsored Brands to see how we’re helping businesses grow on Amazon.com and beyond!

A day in the life (role summary)
As a Software Development Engineer on our team, your days will be immersed in building scalable, production-grade systems that power intelligent advertising experiences for millions of advertisers. You'll partner closely with applied scientists, fellow engineers, and product managers to architect and implement sophisticated agentic systems that seamlessly integrate LLMs with real-time optimization tools, auction simulations, and ML models.
Your work will span the full engineering lifecycle—from designing orchestration layers for agent-to-agent communication, to implementing state management frameworks that persist context across multi-step workflows, to building evaluation pipelines with automated benchmarks and safety guardrails. You'll prototype multi-agent architectures, optimize performance at scale, and ensure reliability through comprehensive observability and telemetry systems. From developing MCP-based tool integrations to deploying streaming pipelines for real-time customizations, you'll contribute to breakthrough innovations that directly impact advertiser success across Ads Console, Seller Central, and Sales experiences.


Key job responsibilities
* Lead engineering strategy and roadmap for SPB Agent Skills and Tools, building specialized sub-agents with domain expertise for performance analysis, recommendations, and targeting optimization
* Design and build agents to guide advertisers in conversational and non-conversational experiences across Ads Console, Seller Central, and Sales
* Implement advanced model and agent optimization techniques, including supervised fine-tuning, instruction tuning, and preference optimization (e.g., DPO/IPO)
* Curate datasets and tools for Model Context Protocol (MCP) integration, enabling seamless agent-to-agent and agent-to-service communication
* Build evaluation pipelines for agent workflows, including automated benchmarks, multi-step reasoning tests, and safety guardrails
* Develop agentic architectures (e.g., CoT, ToT, ReAct) that integrate planning, tool use, and long-horizon reasoning
* Prototype and iterate on multi-agent orchestration frameworks and workflows that enable specialized sub-agents to be invoked as tools or independent agents
* Collaborate with peers across engineering, science, and product to bring innovations into production at scale
* Stay current with the latest developments in LLMs, RL, and agent-based AI, and translate findings into practical engineering solutions serving 1.6MM advertisers