Software Development Engineer , Amazon Robotics (ar) Sortation Planning

Amazon Amazon · Big Tech · N.reading, MA · Software Development

Software Development Engineer role focused on building intelligent, closed-loop decision systems for Amazon Robotics. This involves designing and building agentic AI systems that combine machine learning, real-time data processing, and LLM-driven reasoning to automate operational decision-making in robotic workflows. The role also includes developing end-to-end decision systems, scalable architectures on AWS, ML models, data pipelines, and implementing observability and evaluation frameworks. Collaboration with cross-functional teams and end-to-end ownership of production systems are key aspects.

What you'd actually do

  1. Design and build agentic AI systems that combine machine learning models, real-time data, and LLM-driven reasoning to automate operational decision-making in robotic workflows.
  2. Develop end-to-end decision systems that observe system state, generate insights, and trigger safe, validated actions through robust safeguards and control mechanisms.
  3. Build scalable, event-driven architectures on AWS to support real-time and batch processing for inference, decisioning, and continuous feedback loops.
  4. Design and implement machine learning models for perception, classification, prediction, and optimization, and integrate them into production systems.
  5. Develop and manage data pipelines, model training workflows, and deployment infrastructure, ensuring reliable and scalable ML Ops practices.

Skills

Required

  • Python
  • Java
  • AI frameworks
  • AWS Bedrock
  • Langfuse
  • Agentic AI development
  • machine learning algorithms
  • model evaluation
  • data-driven optimization
  • production ML deployment
  • software development life cycle
  • coding standards
  • code reviews
  • source control management
  • build processes
  • testing
  • operations

Nice to have

  • Master's degree in computer science, machine learning, engineering, or related fields
  • JVM-based languages (Kotlin, Scala)
  • software architectures
  • continuous deployments
  • operational excellence

What the JD emphasized

  • agentic AI systems
  • LLM-driven reasoning
  • real-time data
  • robotic workflows
  • AWS
  • ML Ops practices
  • observability
  • evaluation frameworks
  • end-to-end ownership

Other signals

  • building intelligent platforms
  • agentic AI systems
  • ML Ops
  • intelligent decision systems
  • real-time data processing
  • LLMs