Senior Data Scientist, Amazon Global Logistics

Amazon Amazon · Big Tech · Boston, MA · Data Science

Senior Data Scientist role focused on developing and deploying machine learning models and AI agents for logistics optimization, fraud detection, and revenue management. The role involves end-to-end model development, from data analysis to production deployment and monitoring, with a focus on agentic AI systems and ML-powered fraud detection.

What you'd actually do

  1. Develop ML-powered systems for marketing effectiveness, fraud detection, revenue management, and economic value modeling
  2. Own end-to-end model development from exploratory analysis to deployment and monitoring
  3. Define, track, and explain success metrics to measure model impact and inform decision-making
  4. Build business cases to support science initiatives and model prioritization
  5. Write technical papers and submit work to internal and external conferences and publications

Skills

Required

  • 5+ years of data querying languages (e.g. SQL), scripting languages (e.g. Python) or statistical/mathematical software (e.g. R, SAS, Matlab, etc.) experience
  • Master's degree in computer science, engineering, mathematics or equivalent
  • 5+ years of data scientist experience
  • Experience with Machine Learning and Large Language Model fundamentals, including architecture, training/inference lifecycles, and optimization of model execution, or experience in machine learning, data mining, information retrieval, statistics or natural language processing
  • Experience working with cross-functional teams across business development, marketing, operations, product development, legal, etc.
  • Comfort navigating between strategic work and exploratory analysis

Nice to have

  • Knowledge of AWS tech stack (e.g., AWS Redshift, S3, EC2, Glue)
  • Experience as a leader and mentor on a data science team
  • 2+ years of data visualization using AWS QuickSight, Tableau, R Shiny, etc. experience
  • Experience documenting modeling for technical and business leaders

What the JD emphasized

  • production-ready solutions
  • deployment and monitoring
  • model impact
  • model prioritization
  • agentic AI systems
  • fraud detection models
  • revenue management systems
  • economic value models
  • theft detection model accuracy
  • pricing models
  • agentic marketing solutions
  • productionizing models
  • capacity forecasts
  • routing constraints
  • theft detection workflows
  • modeling approaches
  • technical initiatives
  • intelligent pricing systems
  • seller churn
  • GenAI applications
  • fraud detection systems
  • routing optimization models
  • seller experience
  • Machine Learning and Large Language Model fundamentals
  • architecture, training/inference lifecycles, and optimization of model execution

Other signals

  • Develop ML-powered systems for marketing effectiveness, fraud detection, revenue management, and economic value modeling
  • Own end-to-end model development from exploratory analysis to deployment and monitoring
  • Develop ML-powered systems for marketing effectiveness, fraud detection, revenue management, and economic value modeling