The empowered and agile Data Science & Statistics team is charged with creating analytics systems that enable highly effective product development via virtual experimentation, optimization and knowledge discovery. In addition, the team delivers data science solutions for computer vision automation, Operations, and Supply Chain and offers data science consulting services to the Lubrizol technical community throughout the world. You'll collaborate with a diverse group of passionate individuals to deliver sustainable solutions to advance mobility, improve wellbeing and enhance modern life.
What We're Looking For:
Potential projects (depending on intern skills and current Lubrizol needs):
Create predictive models by mining complex data for critical formulating or testing insights
Implement and assess algorithms in R and Python (SAS, JMP, or C#/C++, optional)
Collaborate with the data science team, as well as scientists and chemical engineers, to understand their needs and find creative solutions to meet those needs
Deploy algorithms and create predictive models by mining complex visual data
Research, develop, and operationalize new statistical, machine learning and/or optimization methods (PhD level)
Previous intern projects include:
Predictive modeling using Bayesian and machine learning methods
R/Shiny tool development to enable model predictions and formulation optimization
Creation of an interactive visualization tool for monitoring predictive models
Development of a bootstrap procedure for a hypothesis test
Multitask learning (transfer learning) using co-regionalized Gaussian Processes (PhD level)
Multivariate variable selection approach using Variational Bayes (PhD level)
Multi-objective optimization using genetic algorithms (PhD level)
Survival modeling using bagged Cox proportional hazards regression trees (PhD level)
Bootstrap variance estimation for complex nonlinear models (PhD level)
Skills That Make a Difference:
Enrolled in a Master’s or PhD program such as statistics, data science, machine learning, or chemical engineering
Dual degree students (e.g., statistics/data science and chemistry, chemical engineering, computational chemistry, etc.) are encouraged to apply
Significant coursework in predictive modeling, Bayesian approaches, and optimization, deep learning, forecasting, multivariate data analysis, and/or generative AI
Able to efficiently manipulate, process, and analyze data of various modalities, including numerical, image, text, and beyond
Advanced programming skills and exposure to data query languages
Interest and experience in advanced statistical and machine learning methodology (PhD level)
Curiosity, creativity, initiative, and autonomy
Perks and Rewards That Inspire:
Preferred location of Wickliffe, OH or Deer Park, TX, but potential for remote work opportunity
Housing and relocation assistance available for eligible students
Competitive hourly wage
Paid holidays within your work period