Machine Learning Engineer

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

Machine Learning Engineer at Amazon Ads focused on building and operating ML systems for ad relevance at scale, including LLM-based systems. The role involves designing data ingestion pipelines, developing ML feature generation services, enhancing training and inference systems, and collaborating with scientists and engineers.

What you'd actually do

  1. Design, build, and operate near-real-time (NRT) data ingestion pipelines using Apache Flink, Kinesis, and DynamoDB that process shopper behavioral signals at scale (100K+ TPS, sub-second latency)
  2. Develop and maintain ML feature generation services that transform raw customer interactions into ML-ready signals consumed by prediction models across Amazon Ads
  3. Enhance the scalability, automation, and efficiency of large-scale training and real-time inference systems.
  4. Build and improve data quality monitoring frameworks, automated alerting, and self-healing mechanisms to ensure signal reliability at 99.9%+ availability
  5. Collaborate with applied scientists and partner engineering teams to onboard new shopper signals, define feature schemas, and optimize serving latency for real-time ad personalization

Skills

Required

  • Machine learning
  • data mining
  • information retrieval
  • statistics
  • natural language processing
  • software development experience
  • design or architecture of new and existing systems experience

Nice to have

  • Bachelor's degree in computer science or equivalent
  • full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

What the JD emphasized

  • ML models
  • LLM-based systems
  • real-time personalization
  • large-scale training and inference

Other signals

  • ML models
  • LLM-based systems
  • real-time personalization
  • large-scale training and inference