Location: Atlanta, GA (Global HQ)
Estimated Travel: 0-20%
Direct Reports : None
The Global Equipment Platforms (GEP) team is seeking an exceptional and highly skilled Data Scientist to unlock the profound value hidden within the telemetry data of The Coca-Cola Company's global fleet of 17MM+ connected equipment. Reporting to the Head of Data within GEP Digital, this individual contributor role is crucial in transforming raw data from beverage vending machines, dispensers, coolers, and retail racks into actionable intelligence that drives revenue growth, reduces operating expenses, and provides unprecedented real-time market understanding.
You will be at the forefront of designing, developing, and deploying advanced analytical models, machine learning algorithms, and potentially AI Agents, leveraging vast datasets from equipment running on the KO Operating System (KOS) and other embedded systems. This role demands a deep technical expert with a proven track record of extracting insights from complex, high-volume data, building robust predictive solutions, and effectively communicating findings to influence strategic decisions across our internal teams, 200+ global franchise bottlers, and OEM partners. Your work will directly enable predictive maintenance, optimize equipment placement, personalize consumer experiences, and inform real-time commercial strategies.
Key Responsibilities:
Advanced Analytics & Model Development (40%):
Lead the end-to-end development of advanced analytical models and machine learning algorithms (e.g., predictive maintenance, anomaly detection, demand forecasting, sales optimization, personalization, inventory management) using diverse equipment telemetry data.
Design and implement statistically sound experiments to test hypotheses and evaluate the impact of digital initiatives on business outcomes.
Explore and apply cutting-edge AI capabilities, including the potential for AI Agents for autonomous decision-making and computer vision solutions for equipment-level insights.
Leverage vast datasets from 17MM+ connected devices, considering the nuances of various equipment @types and global market conditions (premium to ultra low-cost solutions).
Develop and evaluate advanced machine learning models (e.g., predictive maintenance, anomaly detection, demand forecasting, consumer behavior analytics) with a clear pathway for product ionization by the Lead AI Engineer, ensuring insights are actionable and inform product decisions (in partnership with the Product Owner) to drive TCO reduction and revenue growth.
Insight Generation & Storytelling (25%):
Translate complex analytical findings and model results into clear, concise, and actionable business insights for a diverse audience, including senior leadership, Global Customer Commercial teams, and Bottler partners.
Develop compelling data visualizations, dashboards, and presentations to effectively communicate insights and recommendations.
Identify strategic opportunities for leveraging connected equipment data to solve critical business problems, reduce the "fog of war," and create competitive advantage.
Data Exploration & Feature Engineering (20%):
Collaborate closely with Lead Data Engineers to identify, acquire, and prepare high-quality, relevant data from disparate sources (telemetry, sales, customer data, external market data) for analysis and model building.
Perform rigorous exploratory data analysis to uncover hidden patterns, trends, and correlations within complex IoT datasets.
Develop robust feature engineering pipelines that transform raw data into features optimized for machine learning models.
Proactively identify data quality issues and work with data engineering to resolve them, ensuring data integrity and reliability for analytical purposes.
Design and implement robust feature engineering strategies, working closely with the Lead Data Engineer to ensure optimal data preparation and access for model training.
Model Deployment, Monitoring & Optimization (15%):
Work with Data Engineering and Digital Technology Solutions (IT) teams to ensure seamless deployment of machine learning models into production environments (primarily Azure ML, Azure Databricks).
Design and implement robust monitoring frameworks for deployed models, tracking performance, drift, and retraining needs.
Continuously optimize existing models for accuracy, efficiency, and business impact, ensuring they remain relevant and effective over time.
Contribute to the MLOps strategy, ensuring models are versioned, reproducible, and scalable.
Key Deliverables:
Production-ready machine learning models and algorithms delivering measurable business value (e.g., specific reductions in downtime, increases in sales, optimized asset utilization).
Compelling data-driven insights and strategic recommendations presented to key stakeholders.
Comprehensive analytical reports, dashboards, and presentations that track key performance indicators related to equipment fleet performance and business outcomes.
Clean, well-documented code for analytical processes and model development.
Contributions to the development of novel data features and analytical methodologies.
Decision Rights:
Selection of appropriate statistical and machine learning methodologies for specific business problems.
Design and execution of analytical experiments.
Feature selection and engineering for model development.
Interpretation and communication of analytical results and recommendations.
Required Experience & Qualifications:
Bachelor's degree in a quantitative field such as Computer Science, Statistics, Mathematics, Physics, Engineering, or a related discipline. Master's or Ph.D. preferred.
7+ years of hands-on experience as a Data Scientist, with a strong portfolio of successfully deployed machine learning models in production.
Expertise in statistical modeling, machine learning algorithms (supervised, unsupervised, reinforcement learning), and deep learning.
Highly proficient in programming languages commonly used for data science (Python required, R a plus) and relevant libraries (scikit-learn, TensorFlow, PyTorch, Pandas, NumPy).
Strong experience with cloud-based ML platforms and services, particularly Microsoft Azure Machine Learning, Azure Databricks, and related data services.
Demonstrated ability to work with large, complex, and often messy datasets, including time-series data from IoT devices.
Proficiency in SQL for data extraction and manipulation.
Experience in data visualization tools (e.g., Power BI, Tableau, matplotlib, seaborn).
Strong understanding of MLOps principles and practices for model deployment and lifecycle management.
Experience with, or strong understanding of, IoT, connected devices, and telemetry data.
Competencies:
Analytical Acumen & Curiosity :?Possesses a strong ability to structure problems, apply advanced analytical techniques, and continuously learn new methods.
Technical Proficiency :?Deep hands-on expertise in data science tools, programming languages, and ML frameworks.
Business Impact Driver :?Translates complex technical work into clear business value and actionable recommendations.
Communication & Storytelling :?Effectively communicates complex quantitative analysis to non-technical audiences, influencing decisions with data-driven narratives.
Collaborative & Adaptive :?Works effectively with data engineers, product owners, and business stakeholders; adapts to evolving data and business needs.
Innovation & Problem Solving :?Proactively identifies opportunities for leveraging data and AI to solve business challenges and create new capabilities.
Success is measured by:
Business Impact :?Quantifiable improvements in key business metrics (e.g., X% reduction in equipment downtime, Y% increase in transactions, Z% optimization of field service costs) directly attributable to deployed models and insights.
Model Performance & Reliability :?Accuracy, precision, recall, F1-score, and other relevant metrics for deployed models; minimal model drift and high uptime in production.
Insight Adoption :?Rate at which business stakeholders and bottlers adopt and act upon insights and recommendations.
Scalability & Efficiency :?Contribution to building reusable analytical components and optimizing computational resources.
Innovation :?Successful prototyping and deployment of novel AI/ML solutions, including exploration of AI Agents and Computer Vision capabilities.
What We Can Do for You:
Iconic & Innovative Brands : Our portfolio represents over 250 products with some of the most popular brands in the world, including Coca-Cola, Simply, Fairlife & Topo Chico.
Expansive & Diverse Customers : We work with a diversified group of customers which range from retail & grocery outlets, theme parks, movie theatres, restaurants, and many more each day.
Skills Scikit-Learn; Data Science; Python (Programming Language); Statistical Models; Microsoft Azure Databricks; Data Visualization; Tensorflow; PyTorch; Machine Learning Operations; Pandas Python Library; Microsoft Azure Machine Learning; Machine Learning Algorithms; Deep Learning
All persons hired will be required to verify identity and eligibility to work in the United States and to complete the required employment eligibility verification form (Form I-9) upon hire.
Pay Range:$131,000 - $153,000
Base pay offered may vary depending on geography, job-related knowledge, skills, and experience. A full range of medical, financial, and/or other benefits, dependent on the position, is offered.
Annual Incentive Reference Value Percentage:15
Annual Incentive reference value is a market-based competitive value for your role. It falls in the middle of the range for your role, indicating performance at target.
We are an Equal Opportunity Employer and do not discriminate against any employee or applicant for employment because of race, color, sex, age, national origin, religion, sexual orientation, gender identity and/or expression, status as a veteran, and basis of disability or any other federal, state or local protected class.
