Lead Data Scientist (P4296)

Title: Lead Data Scientist (P4296) Location: Cincinnati, OH; Chicago, IL

Lead Data Scientist, Tech Track  (P4296)

Summary:

The SCORe (Supply Chain, Operations, and Replenishment) team is seeking an experienced lead data scientist to act as co-lead developer on one of our core capabilities. This role will be responsible for evolving cutting-edge optimization models and algorithms aimed at improving end to end supply chain operations, with an emphasis on transportation planning. The ideal candidate will have a strong background in development, optimization, and the supply chain domain. Familiarity with 84.51° and Kroger’s data assets would be preferred.

Responsibilities:

• Co-lead the evolution of core optimization science capability including:
• Development of near and long-term analytical plans

• Independently execute work following best-in-class development patterns

• Adding new features for expanded business coverage
• Methods to scale or improve process time of solution
• Refactor code for Object Oriented Programming best practices and production stability.
• Implement ways to leverage coding agents that balances speed of development with responsible/sustainable ownership of code by data scientists and engineers.
• Analyze production code runs to address bugs or bottlenecks in a timely manner.
• Collaborate with cross-functional teams to translate business needs into analytical problems and deliver optimization solutions.

• Develop novel numerical techniques to improve computational efficiency.

• Research upgrades or simplifications to optimization algorithms and develop MVP code.
• Mentor junior team members and guide them through complex problem-solving.
• Collaborate closely on applied customer science initiatives and with other Research Scientists, Data Scientists, Machine Learning Engineers, and contributors across the business.

Qualifications, Skills, and Experience:

• Bachelor's degree in computer science, mathematics, statistics, data science or related discipline
• 4+ years of experience using advanced algorithms, programming languages, or technologies in the development of technical analytics solutions or capabilities.
• Experience using Python to develop analytical solutions.This is a heavy developer role.
  • Excellent understanding of Python data structures
  • Test Driven Development
  • Object Oriented Programming
• Experience guiding data science solutions to production and managing forward:
  • CI/CD
  • Package version management
  • Orchestration
  • Parallelization techniques
• Experience with solving large-scale optimization problems.
• Experience in performing data analysis, cleaning, and orchestration to enable optimization sciences.
• Experience in open-source and commercial solvers (Gurobi, IPOPT, HiGHs, etc.)
• Hands-on experience coding in SQL and PySpark.

• Hands-on experience with technologies such as Azure, Hadoop, Databricks, kubernetes, etc. to create computationally efficient solutions

• Strong interpersonal and communication skills.
• Strong analytical, creative problem-solving and decision-making skills
• Ability to work in a highly collaborative environment.

#LI-SSS