Data Science Co-Op

The Data Science Intern will support the Data Science team in developing and applying statistical and machine learning models to generate actionable insights that drive value across Campbell’s business. This internship offers hands-on experience in time series forecasting, statistical analysis, and predictive modeling within a dynamic CPG environment. The ideal candidate has a strong quantitative foundation, a passion for solving real-world problems with data, and the ability to communicate analytical findings clearly to business stakeholders.

Essential Responsibilities

Responsibilities will include but not be limited to:

• Develop and refine time series forecasting models (e.g., ARIMA, Prophet, exponential smoothing, XGBoost) to support demand planning and supply chain decision-making.
• Apply statistical and machine learning techniques—including regression, classification, clustering, and hypothesis testing—to analyze business data and generate actionable recommendations.
• Conduct exploratory data analysis and statistical testing to identify trends, patterns, and opportunities across product segments and markets.
• Retrieve, cleanse, transform, and analyze complex datasets from multiple sources to support ongoing analytics initiatives.
• Create clear and compelling data visualizations to communicate findings and drive stakeholder buy-in.
• Collaborate with cross-functional teams (Supply Chain, Finance, Marketing, Sales) to identify areas where data science can deliver measurable business impact.
• Support data engineers in evaluating and improving the existing data science infrastructure, tools, and pipelines.
• Document analytical methodologies, assumptions, and results to ensure reproducibility and knowledge sharing.

Requirements

• Currently pursuing an MS or Ph.D. in Statistics, Data Science, Computer Science, Mathematics, Engineering, Operations Research, or a related quantitative field. Ph.D. candidates are strongly preferred.
• Strong foundation in time series analysis and forecasting methods (e.g., ARIMA, SARIMA, exponential smoothing, state-space models, Prophet, or tree-based approaches).
• Solid knowledge of statistical modeling and machine learning, including regression, classification, clustering, dimensionality reduction, and model evaluation techniques.
• Demonstrated experience with statistical analysis: hypothesis testing, confidence intervals, A/B testing, and experimental design.
• Programming: 1+ years of experience in Python and/or R, with proficiency in data science libraries such as Scikit-learn, Pandas, NumPy, SciPy, Statsmodels, and TensorFlow or PyTorch.
• Databases: Familiarity with SQL for data extraction and manipulation.
• Experience with Databricks (PySpark, Spark SQL, MLflow) is a significant plus.
• Familiarity with visualization tools such as Power BI, Matplotlib, Seaborn, or Python Dash is a plus.
• Strong written and verbal communication skills, with the ability to articulate complex analytical concepts in practical terms to non-technical audiences.

Preferred Qualifications

• Ph.D. candidate with research focus in time series forecasting, statistical learning, or applied machine learning.
• Experience working with large-scale datasets in a Databricks or Spark-based environment.
• Familiarity with demand forecasting, supply chain analytics, or CPG industry data.
• Experience with optimization methods (linear programming, mixed-integer programming) using tools such as Gurobi, PuLP, or SciPy.
• Exposure to MLOps practices, including model versioning, experiment tracking (e.g., MLflow), and pipeline automation