Software Development Engineer, Ads AI Core Infra (aci)

Amazon Amazon · Big Tech · Seattle, WA · Software Development

Software Development Engineer focused on building AI agent infrastructure for Amazon Advertising. The role involves designing and implementing scalable systems for AI agents to access and reason over advertiser data, including building the Model Context Protocol (MCP) server infrastructure. It emphasizes agent orchestration, context optimization, and creating feedback loops for continuous improvement, operating at a high-velocity, large-scale distributed systems environment.

What you'd actually do

  1. Design and implement scalable architectures for APIs serving millions of advertisers at thousands of transactions per second
  2. Build Model Context Protocol (MCP) server infrastructure—an emerging standard for AI agent-data interaction—that delivers advertiser context with sub-second latency and minimal token consumption
  3. Establish system design patterns and best practices for global ads experience at scale

Skills

Required

  • 3+ years of non-internship professional software development experience
  • 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
  • Experience programming with at least one software programming language

Nice to have

  • 3+ 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

What the JD emphasized

  • invent new techniques for global ads experience, agent orchestration, and context optimization
  • minimal latency
  • minimal token consumption
  • constantly evaluating themselves and improving

Other signals

  • AI agents access and reason over real-time advertiser data at scale
  • invent new techniques for global ads experience, agent orchestration, and context optimization
  • create feedback loops to ensure our solutions are constantly evaluating themselves and improving
  • Build Model Context Protocol (MCP) server infrastructure—an emerging standard for AI agent-data interaction