Software Development Engineer, Prime Video, Content Understanding

Key job responsibilities

• Design, build, and own services that index and serve Prime Video catalog content to hundreds of millions of customers across 240+ countries
• Build and evolve AI agents that combine LLM reasoning, semantic search, and real-time catalog lookups to power natural language content discovery
• Develop search infrastructure that blends keyword, semantic, and web-based signals with LLM re-ranking to surface the most relevant titles and clips
• Own the full lifecycle of services you build — from architecture and implementation through deployment, monitoring, and operational excellence
• Design and operate low-latency serving infrastructure that delivers search and clip results under strict availability constraints
• Integrate with large language models (Bedrock Claude) and agentic frameworks to build reliable, production-grade AI systems
• Solve complex, ambiguous problems across distributed systems, vector search, and AI agents with minimal guidance
• Improve engineering practices across the team including CI/CD pipelines, testing frameworks, deployment patterns, and on-call processes
• Mentor engineers on system design, code quality, and AI/ML best practices
• Collaborate with scientists, product managers, and partner teams to translate business problems into well-scoped technical solutions and influence the technical roadmap

About the team

We are the MediaCoreExpert (MCX) team within Prime Video's Content Understanding Platform. We own the systems that decide what a customer finds when they search for something. Our mission is to make content discovery effortless by building AI agents, search infrastructure, and catalog intelligence that understands Prime Video content at a semantic level — and surfaces the right title, scene, or clip for every customer query. We operate with high ownership and low bureaucracy. Engineers own systems end-to-end and are trusted to make decisions autonomously. We debate openly, experiment rigorously, and ship fast. This is a Day 1 team solving greenfield problems at the frontier of LLMs and content search at worldwide scale.

Basic Qualifications

• 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

Preferred Qualifications

• 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