Sr. Software Development Engineer, Amazon Shopping (rufus)

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

Senior Software Development Engineer role focused on building and scaling agentic AI applications powered by large language models for Amazon's shopping experience. The role involves architecting, designing, and developing back-end systems, online services, service orchestration patterns, and efficient agent frameworks. It also includes contributing to the technical roadmap, service reliability, and optimizations for intelligent agents that reason, plan, and execute tasks. The position emphasizes improving LLM application efficiency and enabling new agentic AI features.

What you'd actually do

  1. architect, design, and develop agentic services and applications powered by large language model
  2. build expertise in online service architecture, API development, and distributed systems that power responsive agentic AI applications at scale
  3. 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
  4. 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
  5. help establish best practices that improve LLM application efficiency, enable new agentic AI features for Stores customers with LLM capabilities

Skills

Required

  • 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
  • Knowledge of Machine Learning and LLM fundamentals, including transformer architecture, training/inference lifecycles, and optimization techniques

Nice to have

  • 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
  • Experience with vLLM, SGLang, TensorRT or similar platforms in production environments, or experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware
  • 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

What the JD emphasized

  • expertise in back-end system and online service
  • agentic services and applications powered by large language model
  • online service architecture, API development, and distributed systems
  • responsive agentic AI applications at scale
  • service orchestration patterns, efficient agent frameworks
  • intelligent agents that can effectively reason, plan, and execute complex tasks
  • LLM application efficiency
  • agentic AI features
  • large scale distributed agentic AI applications at scale
  • Experience with vLLM, SGLang, TensorRT or similar platforms in production environments, or experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware
  • 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

Other signals

  • building agentic services
  • large scale distributed agentic AI applications
  • improving LLM application efficiency
  • develop service orchestration patterns
  • efficient agent frameworks
  • real-time processing systems