Software Development Engineer , Adaptive Search Relevance

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

Build and scale a multi-agent orchestration platform for autonomous ML research workflows, from hypothesis generation to production deployment, accelerating relevance improvements for millions of shoppers. The role involves AI-first engineering at the intersection of Generative AI, large-scale ML infrastructure, and search relevance, focusing on platform reliability, developer experience, and productionizing LLM/VLM models with low-latency serving.

What you'd actually do

  1. Build and scale a multi-agent orchestration platform that autonomously executes research workflows — from hypothesis generation and experiment design through training, evaluation, and production deployment — with fault tolerance, cost controls, and security compliance
  2. Develop AI-first Auto Research systems that parallelize hypothesis testing across compute, incorporating tournament-based proposal filtering and human-in-the-loop review to dramatically increase scientist throughput
  3. Own platform reliability and developer experience, including multi-tenant GPU scheduling, observability, eval frameworks, and knowledge services — ensuring agents and scientists operate on a stable, extensible foundation
  4. Productionize LLM/VLM models with a focus on efficiency, throughput, and low-latency serving
  5. Collaborate with scientists and engineers to design and build data pipelines for processing massive datasets and scaling ML and LLMs

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
  • 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
  • Knowledge of Machine Learning and LLM fundamentals, including transformer architecture, training/inference lifecycles, and optimization techniques
  • Demonstrated track record of innovative AI agent solution development

What the JD emphasized

  • multi-agent orchestration platform
  • autonomously executes research workflows
  • production deployment
  • AI-first engineering
  • scientist throughput
  • LLM/VLM models
  • low-latency serving
  • data pipelines
  • ML and LLMs
  • customer-perceived relevance
  • generative AI technologies
  • responsible and intelligent AI technologies
  • innovative AI agent solution development

Other signals

  • multi-agent orchestration platform
  • autonomous ML research workflows
  • Generative AI
  • large-scale ML infrastructure
  • search relevance at massive scale
  • AI-first engineering
  • scientist throughput
  • production deployment
  • LLM/VLM models
  • low-latency serving
  • data pipelines
  • ML and LLMs
  • customer-perceived relevance
  • generative AI technologies
  • responsible and intelligent AI technologies