Software Development Engineer, Amazon Shopping

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

Software Development Engineer to architect, design, and develop agentic services and applications powered by large language models for Amazon Shopping. The role focuses on building expertise in online service architecture, API development, and distributed systems for responsive agentic AI applications at scale, including service orchestration, agent frameworks, and real-time processing. The goal is to establish best practices, enable new agentic AI features, and contribute to the technical roadmap for intelligent agents that reason, plan, and execute complex tasks.

What you'd actually do

  1. build expertise in online service architecture, API development, and distributed systems that power responsive agentic AI applications at scale
  2. develop service orchestration patterns, efficient agent frameworks, and real-time processing systems, partnering with engineers and scientists in a fast-paced environment to deliver exceptional user experiences
  3. contribute to our technical roadmap, service reliability metrics, and optimizations focused on building intelligent agents that can effectively reason, plan, and execute complex tasks on behalf of users
  4. help establish best practices that improve LLM application efficiency, enable new agentic AI features for Stores customers with LLM capabilities
  5. design, implement large scale distributed agentic AI applications at scale, partnering with technical and business leaders in a collaborative environment to create value for our customers

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
  • 1+ years of software development engineer or related occupational experience
  • 1+ years of designing and developing large-scale, multi-tiered, multi-threaded, embedded or distributed software applications, tools, systems, and services using: C#, C++, Java, or Perl experience
  • 1+ years of Object Oriented Design experience
  • Knowledge of Machine Learning and LLM fundamentals, including transformer architecture, training/inference lifecycles, and optimization techniques

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
  • Experience building or operating LLM-powered agent systems (tool use, ReAct loops, multi-step orchestration)
  • Experience with agent evaluation frameworks — offline evaluation, LLM-as-Judge, composite scoring, or quality measurement at scale.
  • Experience hosting or serving large language models at scale (model deployment, inference optimization, GPU cluster management, vLLM/TensorRT)

What the JD emphasized

  • agentic services
  • agentic AI applications
  • agent frameworks
  • intelligent agents
  • agentic AI features
  • agentic AI applications
  • agent evaluation frameworks

Other signals

  • building agentic services
  • large scale distributed agentic AI applications
  • AI-first initiative to further improve the way we do search using large-scale foundation models