Director, Supply Chain Lead Data Scientist

Coca-Cola; Georgia; On-site; USD 120,000 - 170,000; Full time

Job summary

Coca-Cola's Supply Chain Digital Enablement team seeks a Data Scientist to build analytical products that improve how supply-chain teams decide. You will partner with Supply Chain, Operations, Product, Engineering, Data, Commercial, and Finance to translate ambiguous business problems into scalable models and AI-enabled decision support.

This role combines statistical analysis, predictive modeling, optimization, simulation, and modern AI techniques.

Qualifications

• 7+ years applying data science, ML, optimization, or analytics in business or supply-chain environments.
• Proven technical leadership delivering complex data-science products from problem definition through production adoption.
• Advanced Python and SQL; scalable data, model, and ML architecture patterns.
• Deep expertise in predictive modeling, optimization, simulation, NLP, deep learning, or agentic systems.
• Experience designing MLOps including CI/CD, model registries, testing, monitoring, drift detection, retraining, and incident response.
• Ability to evaluate algorithmic complexity, trade-offs, scalability, explainability, and operating cost.
• Proven ability to influence senior stakeholders, guide cross-functional delivery, and mentor other data scientists.

Responsibilities

• Develop, evaluate, and productionize predictive, prescriptive, optimization, simulation, and NLP models for supply-chain decisions
• Translate planning, inventory, transportation, manufacturing, network, and service problems into clear analytical requirements, model approaches, and measurable outcomes
• Design ML architectures and rapid prototypes; partner with Engineering and Data teams to scale successful solutions into reliable products
• Apply optimization and simulation methods, evaluating algorithmic complexity, performance, scalability, and trade-offs
• Apply statistical analysis, forecasting, causal methods, and experimental design to evaluate interventions and quantify business impact
• Partner with data engineering to ensure trustworthy data architecture, scalable pipelines, data-quality foundations
• Build model lifecycle practices including reproducibility, versioning, testing, deployment, monitoring, drift detection, retraining, and documentation
• Evaluate and apply deep learning, large language models, NLP, and agentic systems where they create measurable value with appropriate controls and human oversight
• Apply AI governance, privacy, security, fairness, explainability, and responsible-AI principles throughout development and deployment
• Communicate technical choices, insights, limitations, and recommendations clearly to stakeholders
• Contribute to cross-functional software lifecycle management from discovery to deployment and support
• Define technical strategy, reference architectures, and modeling standards for priority data-science products
• Mentor data scientists and review technical designs, model quality, deployment readiness, and responsible-AI controls

Skills

Data science leadership

Python & SQL proficiency

ML/AI modeling

MLOps practices

Model governance

Stakeholder communication

Supply chain problem solving

Job description

Job Description Summary

Job Summary

Supply Chain Digital Enablement applies data, analytics, and artificial intelligence to improve planning, service, cost, resilience, and execution across the North America Operating Unit. Our teams turn complex operational decisions into scalable digital capabilities that create measurable value for customers, bottlers, and the business.

Our work spans demand planning, inventory and replenishment, transportation, manufacturing, customer service, and network decisions. Strong data foundations, rigorous experimentation, optimization, and responsible AI are essential to building solutions that teams trust and use.

About the Role

As a Data Scientist in Supply Chain Digital Enablement, you will build analytical products that improve how supply-chain teams make decisions. You will partner with Supply Chain, Operations, Product, Engineering, Data, Commercial, and Finance colleagues to translate ambiguous business problems into scalable models, optimization tools, simulations, and AI-enabled decision support.

This role combines statistical analysis, predictive modeling, optimization, simulation, and modern AI techniques. You will lead the technical direction for complex, high-value solutions and establish reusable architecture, MLOps, evaluation, and governance practices that raise capability across the team. We are looking for someone with intellectual curiosity, technical rigor, practical supply-chain judgment, and a collaborative approach to delivery.

What You Will Do

• Develop, evaluate, and productionize predictive, prescriptive, optimization, simulation, and NLP models for supply-chain decisions
• Translate planning, inventory, transportation, manufacturing, network, and service problems into clear analytical requirements, model approaches, and measurable outcomes
• Design ML architectures and rapid prototypes; partner with Engineering and Data teams to scale successful solutions into reliable products
• Apply optimization and simulation methods, evaluating algorithmic complexity, performance, scalability, and trade-offs
• Apply statistical analysis, forecasting, causal methods, and experimental design to evaluate interventions and quantify business impact
• Partner with data engineering to ensure trustworthy data architecture, scalable pipelines, robust querying, instrumentation, and data-quality foundations
• Build model lifecycle practices including reproducibility, versioning, testing, deployment, monitoring, drift detection, retraining, and documentation
• Evaluate and apply deep learning, large language models, NLP, and agentic systems where they create measurable value with appropriate controls and human oversight
• Apply AI governance, privacy, security, fairness, explainability, and responsible-AI principles throughout development and deployment
• Communicate technical choices, assumptions, insights, limitations, and recommendations clearly to technical and nontechnical stakeholders
• Contribute to cross-functional software lifecycle management from discovery and prototyping through deployment, adoption, support, and continuous improvement
• Define technical strategy, reference architectures, and modeling standards for priority supply-chain data-science products
• Mentor data scientists and review technical designs, model quality, deployment readiness, and responsible-AI controls

What You Will Need

Key Qualifications

• 7+ years applying data science, machine learning, optimization, forecasting, or advanced analytics in a business, digital, operations, or supply-chain environment
• Demonstrated technical leadership delivering complex data-science products from problem definition through production adoption and measurable business impact
• Advanced Python and SQL skills and experience designing scalable data, model, and ML architecture patterns
• Deep expertise in several of predictive modeling, optimization, simulation, statistical inference, experimental design, NLP, deep learning, or agentic systems
• Experience designing MLOps practices including CI/CD, model registries, testing, monitoring, drift detection, retraining, and incident response
• Ability to evaluate algorithmic complexity, trade-offs, scalability, explainability, and operating cost when selecting solution approaches
• Experience establishing responsible-AI and model-governance practices, including documentation, review, risk controls, and human-in-the-loop decision design
• Proven ability to influence senior stakeholders, guide cross-functional delivery, and mentor other data scientists

Preferred Qualifications

• Significant supply-chain experience in demand planning, inventory, replenishment, manufacturing, logistics, network design, route optimization, or service operations
• Experience leading enterprise-scale optimization, simulation, ML-platform, or AI-product initiatives
• Experience setting technical standards across Data Science, Data Engineering, Product, and Software Engineering teams
• Experience assessing and deploying gen