Senior Data Scientist

About the Position

Join PepsiCo as a Senior Data Scientist to analyze consumer data and optimize product preferences using advanced machine learning techniques.

Responsibilities

• Analyze consumer data: Determine product preferences by analyzing quantitative and qualitative consumer data to obtain insights on the type of products that the target consumers prefer.
• Utilize machine learning: Use statistical methods along with emerging machine learning techniques to identify and recommend alternative solutions to optimize project needs and research objectives in Sensory & Consumer Science, Food Science, Regulatory, Quality Assurance, Supply Chain, Sales & Marketing.
• Develop models: Develop computer/machine vision models and utilize Robotic Process Automation to process raw data and detect data anomalies that can impact data integrity and accuracy of results.
• Present research: Present research outcomes in internal and external meetings and conferences to demonstrate PepsiCo's research capabilities and obtain relevant feedback to improve current research.
• Benchmark models: Routinely develop novel statistical/machine learning models and benchmark them against established (or traditional) modeling techniques to ensure added value of the new models to the PepsiCo R&D processes.
• Optimize methodologies: Research emerging methodologies that can optimize prediction models, such as data augmentation techniques for regression problems.
• Utilize cloud platform: Utilize Microsoft Azure to automatically process large volumes of data for statistical modeling, training machine learning prediction models, graphical visualization via dashboards and web applications, as well as model/application deployment in production environment.
• Provide insights: Utilize experimental design methodology, and Graph Neural Network techniques, to provide insights to product developers, food scientists, and sensory scientists on the optimum combinations of ingredients that go into PepsiCo's products.
• Develop data solutions: Develop new data warehouse strategy and solutions to ensure data integrity and completeness and migrate data warehouse from Access Database/Teradata/Microsoft SQL Server to the Azure cloud, using Azure SQL/Azure Blob Storage/Azure Databricks & Data Lake.
• Develop BI Dashboard: Develop BI Dashboard (Power BI/Tableau) and Web Application, using Python and C# as the delivery of statistical models and machine learning models for key stakeholders for routine data analysis tools and visualization to draw business insights.
• Predictive maintenance: Develop end-to-end predictive maintenance and anomaly detection models on PepsiCo’s plants, e.g., manufacturing data and warehouse pallet data, with production deployment on IoT edge devices to achieve real-time monitoring and predictions to avoid production downtime.

Requirements

• Education: Master’s degree (U.S. or foreign equivalent) in Predictive Analytics, Statistics, Data Science, or related field.
• Experience: Three (3) years of experience in the job offered or related role.
• Skills:
  • Developing forecasting models and reports using machine learning/statistical approach with sales data, demand planning data, or financial data.
  • Conducting quantitative analysis in assortment optimization and trending analysis in corporate/production environment.
  • Conducting qualitative analysis from consumer-related data.
  • Developing anomaly detection models and root-cause analysis.
  • Building end-to-end advanced predictive analytics in production environment for demand forecasting, supply chain optimization, and financial planning.
  • Building robotic process automation tools to manipulate different structured and unstructured data sources.
  • Extract insights and generate automated reporting in cloud (Azure) production environment using SAS, Teradata, Python, SSIS, VBA, and MS SQL.
  • Writing code in ASP.NET and C# for back-end web application development, and HTML for front-end web application development.
  • Writing code in Python, SAS, SQL, and VBA for processing and analyzing large complex data from multiple sources, and shipping code into production.
  • Creating data visualization dashboards for business intelligence using MS Power BI, Tableau, or Python Flask/Dash and published for production usage.
  • SQL, NoSQL, ETL processing, and metadata management in batch mode and streaming mode with Microsoft SQL Server, Teradata, MS Access, and SAS, and big data distributed tools/system.
  • Cloud computing platform, including Microsoft Azure (Azure Web App, Azure DevOps, Azure HDInsight, Azure Cognitive Services, Azure SQL Database, and Azure ML) to develop and deploy end-to-end advanced analytics and robotic process automation solutions.
  • Two (2) years of experience building end-to-end Computer Vision (2D & 3D domains) and Predictive Maintenance solutions, Natural Language Processing models, and Graph Network Analysis, with various deep learning frameworks, and deploy in IoT edge devices and cloud (Azure) production environment.

We Offer

• Competitive salary
• Full-time employment
• Opportunities for domestic travel (within U.S.) to other PepsiCo, Inc. offices

About the Company

PepsiCo is an equal opportunity employer. Minorities/Females/Disability/Protected Veteran/Sexual Orientation/Gender Identity. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, or disability status.

COVID-19 vaccination is a condition of employment for this role. Please note that all such company vaccine requirements provide the opportunity to request an approved accommodation or exemption under applicable law.

For more information about your EEO rights as an applicant under the law, please download the available EEO is the Law & EEO is the Law Supplement documents. View PepsiCo EEO Policy.

Please view our Pay Transparency Statement.