Sr Data Scientist - Global Supply Chain and Logistics

Target · Retail · Ste 100 Sunnyvale, CA

Sr Data Scientist role focused on Global Supply Chain and Logistics, leveraging operations research, simulation, and machine learning to develop and deploy optimization and ML algorithms at scale. Requires strong computer science fundamentals, experience with production deployments, and proficiency in mathematical modeling and programming languages.

What you'd actually do

  1. Work closely with fellow data scientists to review and iterate on optimization and machine learning algorithms and develop state of the art mathematical models
  2. Collaborate with engineers to design and deploy algorithms in production at scale. Our models run many times a day for millions of combinations of stock keeping units and distribution networks
  3. Work with business partners to learn about the retail business and processes in play
  4. Ideate and resolve tradeoffs between model granularity and features as well as performance, reliability, and usability of our codebase. Improve engineering standards, tooling, and processes

Skills

Required

  • Supply chain optimization (inventory, transportation, sourcing, distribution, fulfillment, planning)
  • Computer science fundamentals (data structures, algorithms, programming languages, information retrieval)
  • Writing understandable, testable code with an eye towards maintainability
  • Python, R, Kotlin, or Java
  • Mixed-integer programming, stochastic dynamic programming and reinforcement learning
  • Advanced statistical techniques (regression, clustering, PCA, time series forecasting)
  • Application/software architecture
  • SQL/Hive or building internal/production data tools in Python
  • Communication skills
  • Self-driven and results oriented
  • Collaborative team player

Nice to have

  • PhD or MS in Operations Research, Industrial Engineering, Computer Science, Mathematics, Statistics, Physics, or related quantitative fields
  • 3+ years of experience leading large-scale implementations of optimization, simulation, machine learning and deep learning modeling at scale

What the JD emphasized

  • state of the art mathematical models
  • production at scale
  • highly performant code
  • deploying algorithms in a production environment
  • advanced statistical techniques

Other signals

  • machine learning
  • optimization algorithms
  • production at scale