Data Scientist

Union Pacific
Omaha, Nebraska, United States View on Map
Apply Before : September 9, 2024
Job Description

UPā€™s Advanced Analytics team is looking for a data scientist who is passionate about turning data insights into action. The team is responsible for using machine learning, predictive analytics, text mining, forecasting techniques, operations research, and statistical analysis to solve problems for the enterprise. Ideal candidates will have knowledge and experience with applied mathematical/statistical modeling. Candidates should be able to identify and apply mathematical optimization techniques for efficient resource utilization or be able to use advanced statistical modeling for building competitive intelligence programs.


  • Uncover, learn, and understand business problems, processes, and their characteristics.
  • Create machine learning solutions for various business problems.
  • Design, develop and implement mathematical modeling and optimization algorithms to deliver improvements in business processes.
  • Design, develop and implement predictive and descriptive data mining models to support data driven decision making.
  • Interpret and analyze results of predictive/data mining models.
  • Analyze, explain, communicate and document model results with expanded project team.
  • Follow through to ensure models meet stakeholderā€™s needs and are incorporated into existing systems or workflows.



  • Advanced problem solving skills
  • Customer-focused AND goal-oriented
  • Experience with Scripting and coding languages such as: Bash, Perl, Python, Go or Java
  • Knowledge and experience with RHEL / CentOS
  • A Bachelor’s degree or commensurate experience
  • Analytical and detail oriented
  • 4+ years of work experience


  • Experience with Python, R, MatLab, SAS, SPSS or equivalent statistical software package/language
  • Experience solving analytical problems using statistical/mathematical modeling/methods
  • Experience with applied statistics, machine learning, and predictive model development against diverse data sets
  • Experience with any Operations Research software package (e.g., GUROBI, CPLEX, XpressMP, GAMS, SimProcess)
  • Knowledge in one or more of the following techniques: Linear Regression, Logistical Regression, CARTS, Random Forest, Queuing Theory, Neural Networks, Deep Learning, Clustering
Required skills