Software Development Engineer, Prime Video

Amazon Amazon · Big Tech · NY +1 · Software Development

Software Development Engineer for Prime Video's Discovery Engineering team, focusing on building AI-powered content discovery systems. This involves designing and operating low-latency serving systems for personalized recommendations, large-scale ML pipelines for content processing, and automated evaluation systems. The role requires a strong software engineering foundation and experience with applied machine learning, information retrieval, and distributed systems.

What you'd actually do

  1. Low-latency online serving systems that retrieve and rank personalized recommendations in real time, combining behavioral and semantic embeddings, approximate nearest-neighbor retrieval, cross-encoder rerankers, and diversity-aware ranking.
  2. Large-scale offline data and ML pipelines that generate, classify, embed, and index content using large language models and embedding models, orchestrated across managed workflow and inference infrastructure.
  3. Automated quality and evaluation systems that measure relevance, personalization, diversity, and trust and safety using LLM-based judges and offline metrics, so we can ship improvements with confidence.
  4. The AWS infrastructure behind all of it, defined as code, along with the experimentation framework used to A/B test changes and measure real customer impact.

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
  • Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field
  • 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
  • passion for applied machine learning
  • information retrieval
  • large-scale distributed systems
  • distributed services
  • data pipelines
  • ML model integration in a production environment

What the JD emphasized

  • build the next generation of AI-powered content discovery
  • large-scale machine learning models in a production environment
  • information retrieval problems
  • large language models
  • embedding models
  • LLM-based judges

Other signals

  • build the next generation of AI-powered content discovery
  • turn large language models, embeddings, and semantic retrieval into customer experiences
  • Low-latency online serving systems that retrieve and rank personalized recommendations in real time
  • Large-scale offline data and ML pipelines that generate, classify, embed, and index content using large language models and embedding models
  • Automated quality and evaluation systems that measure relevance, personalization, diversity, and trust and safety using LLM-based judges and offline metrics