Learning Analytics Data Scientist
About The Position
Penn State IT invites a Learning Analytics Data Scientist to join the Data Empowered Learning team. The role supports the creation of models and insights that power tools such as Course Insights and Elevate. The successful candidate will contribute to a collaborative, mission-driven effort to deliver insights that enhance student success and institutional efficiency across Penn State, applying expertise across the data science lifecycle—from organizing complex institutional datasets to using advanced analytical and modeling methods. The position involves designing, validating, and deploying predictive and descriptive models; architecting and maintaining workflows for institutional data; and using exploratory analysis and machine learning to produce actionable recommendations. The Data Scientist will work with university leadership, communicate findings to technical and non-technical audiences, and partner with software developers to bring successful models into production applications used across the university.
Requirements
- Extensive experience with the Python data stack, including pandas and NumPy, for data cleaning, feature engineering, and statistical modeling.
- Robust background in quantitative methods, including regression, clustering, decision trees, and experimental design.
- Expertise writing complex SQL queries to extract and manipulate data in relational databases.
- Proven ability to communicate technical findings clearly and compellingly to non-technical, executive-level stakeholders.
- Exceptional attention to detail and commitment to ethical data use in education.
- Experience managing production-level data and code using version control and CI/CD workflows, such as GitHub Actions or similar automation tools.
- Master's degree and 6 or more years of relevant experience, or an equivalent combination of education and experience.
- Must be authorized to work in the United States; Penn State does not sponsor or take over sponsorship of staff employment visas.
- Successful completion of required background checks.
Nice To Haves
- Degree in Data Science, Computer Science, Information Science, or a related field.
- Experience inheriting production-level codebases or comfort debugging, refactoring, and improving unfamiliar codebases.
- Familiarity with R for supplementary statistical analysis or collaborative research scripts.
- Experience with data visualization libraries such as Plotly or Matplotlib.
- Experience architecting and deploying RESTful APIs to serve machine learning models using frameworks such as FastAPI or Plumber.
- Understanding of the higher education ecosystem, including FERPA compliance and SIS and LMS data structures.
Responsibilities
- Design, validate, and deploy predictive and descriptive models, including models for student-at-risk indicators and engagement patterns, to inform institutional strategy.
- Retrieve and organize institutional data from diverse sources, including Canvas, Starfish, and Student Information Systems, and architect and maintain complex data workflows.
- Use exploratory data analysis and machine learning to identify trends and develop actionable recommendations from raw data.
- Collaborate with university leadership to translate insights into practical, intuitive tools for faculty and advisors.
- Communicate about data and methodological questions with technical and non-technical stakeholders and audiences.
- Partner with software developers to transition successful models into production-level applications used across the university.
Benefits
- Medical, dental, and vision coverage.
- Retirement plans.
- Paid time off, including holidays, vacation, and sick time.
- 75% tuition discount for employees and eligible spouses and children.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
