Sr. Mle, Prime Video ML Platform

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

Senior MLE role focused on building and evolving the ML platform for Prime Video personalization, including model serving, feature delivery, training pipelines, and inference systems. The role involves technical leadership, mentoring, and driving best practices for scalable and resilient ML solutions.

What you'd actually do

  1. Building ML platform services with Tier-1 availability and performance characteristics while enabling rapid model iteration and experimentation for scientists.
  2. Evolving the model serving and feature delivery infrastructure to enable continuous experimentation and keep pace with innovations in state-of-the-art ML capabilities.
  3. Designing and scaling training pipelines, real-time inference systems, and feature stores that support the constantly evolving landscape of Prime Video personalization across Movies, TV Shows, Live Sports, Linear TV, and beyond.
  4. Leading and partnering on developing the strategic technical vision for the PV ML Platform, including model lifecycle management, online/offline evaluation, and serving optimization.
  5. Partnering with Scientists, Product Managers, and Engineering stakeholders to translate research breakthroughs into production-grade platform 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 ML frameworks including JAX, PyTorch, vLLM, SGLang, Dynamo, TorchXLA, and TensorRT
  • 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
  • Bachelor's degree in computer science or equivalent

What the JD emphasized

  • Tier-1 availability
  • rapid model iteration
  • state-of-the-art ML capabilities
  • real-time inference systems
  • constantly evolving landscape
  • strategic technical vision
  • production-grade platform capabilities

Other signals

  • ML platform services
  • model serving
  • training pipelines
  • inference systems
  • personalization