Applied Scientist , Inbound Systems

Amazon Amazon · Big Tech · NY +1 · Applied Science

This role focuses on designing, deploying, and engineering large-scale optimization and forecasting models for Amazon's supply chain. It involves shaping the mathematical architecture of planning systems, pushing computational frontiers, and delivering scientific solutions into production that directly impact real-world inventory movement for millions of customers. The work spans operations research, machine learning, and probabilistic forecasting, with an emphasis on delivering robust, scalable, and performant systems.

What you'd actually do

  1. Build state-of-the-art, robust, and scalable stochastic optimization and probabilistic forecasting algorithms that drive optimal planning and execution under uncertainty across Amazon's end-to-end supply chain
  2. Shape how large-scale planning problems are formulated, decomposed, and solved — designing for computational performance and reliability at the scale of Amazon's fulfillment network
  3. Engineer your algorithms as production-grade, cloud-native software, applying modern development practices from prototype through deployment
  4. Think several steps ahead: architect long-term scientific solutions while continuously shipping incremental improvements to what's already running
  5. Prototype fast, drive early adoption through pilots, integrate operational feedback, and iterate

Skills

Required

  • large-scale optimization
  • stochastic optimization
  • decomposition methods
  • machine learning
  • probabilistic forecasting
  • delivering complex scientific systems end to end
  • Java
  • C++
  • Python
  • algorithms and data structures
  • parsing
  • numerical optimization
  • data mining
  • parallel and distributed computing
  • high-performance computing

Nice to have

  • Unix/Linux
  • professional software development

What the JD emphasized

  • large-scale optimization
  • probabilistic forecasts
  • solver performance at scale
  • move real inventory for hundreds of millions of customers
  • track record of delivering complex scientific systems end to end
  • solves in two seconds or two hundred

Other signals

  • large-scale distributed optimization
  • probabilistic forecasts
  • solver performance at scale
  • move real inventory for hundreds of millions of customers