Current Opportunities at Vanderbilt

Postdoctoral Scholar: AI and Learning Analytics for Tutoring and Student Pathways
Location: Vanderbilt University (Nashville, TN, USA; on-site)
Start Date: Flexible based on candidate availability, preferably by Fall 2026
Duration: 1 year, renewable
Supervisor: Conrad Borchers, c.borchers@vanderbilt.edu, Assistant Professor of Artificial Intelligence in Education, Policy, and Organizations at Vanderbilt University

About the Position:
The Learning, AI & Pathway Systems (LAPS) Lab at Vanderbilt University is recruiting 1-2 Postdoctoral Scholars. The LAPS Lab develops computational approaches for understanding learning, educational systems, and AI-supported instruction, with a particular focus on effort, agency, tutoring, and student pathways across K-12 and higher education. Depending on the candidate's interests and background, appointments may follow one of two research tracks:

Track A (Department of Computer Science): Computational Models of AI, Educational Systems, and Student Pathways
This position focuses on computational modeling of educational pathways, workload, effort, agency, AI-based tutoring, and learning analytics.

Track B (Department of Leadership, Policy, and Organizations): AI-Supported Tutoring and Goal Setting
This position focuses on understanding and improving the effectiveness of large-scale tutoring programs through computational modeling, randomized field experiments, and AI-supported instructional and motivational interventions. Current projects investigate adaptive goal setting, tutor effectiveness, learner persistence, tutoring dialogue, and the integration of AI into technology-supported tutoring through partnerships with K-12 schools. The postdoctoral scholar will actively collaborate with the PLUS Tutoring project at Carnegie Mellon University led by Ken Koedinger.

Applicants are welcome to indicate interest in either track or both.

This position is intended for an early-career scholar interested in helping shape a new interdisciplinary research agenda at the intersection of AI, learning sciences, learning analytics, and educational policy. The postdoc will collaborate on the development of computational and statistical approaches for understanding how students navigate educational systems (broadly conceived to include higher education degree programs and AI-based learning environments) under varying levels of structure, challenge, guidance, and choice, as well as under varying student-level resources and characteristics (e.g., prior knowledge, personality traits, goals).

The lab studies these questions using large-scale longitudinal and interaction data, with interests spanning student trajectories, workload and enrollment behavior, prerequisite networks, adaptive support systems, and moment-to-moment learning processes within AI-driven educational technologies. Current projects include computational modeling of student effort during tutoring interactions, sequence models of educational pathways, and statistical approaches for understanding variation in how students respond to different levels of difficulty and instructional support in AI-based learning environments, including but not limited to tutoring systems, large language models, and technology-augmented human tutoring.

We are especially interested in candidates with strong methodological interests in areas such as computational modeling, representation learning, statistical inference, sequential modeling, machine learning, causal inference, network analysis, or multimodal educational data. Prior experience in education and familiarity with psychological theories of learning and motivation are desirable but not required. The strongest candidates will be technically versatile, theoretically curious, and excited about contributing to the intellectual direction of a growing research lab. This position is also especially well-suited for candidates interested in developing novel theory through computational methods, beyond applying machine learning approaches to educational data.

Research Areas:

Track A: AI, Learning Analytics, and Educational Systems

• Computational modeling of student pathways and educational trajectories
• Representation learning for natural language interactions and educational sequences
• Predictability, constraint, and complexity in educational systems
• Student agency, decision-making, and choice under constraints
• Workload, effort, motivation, and persistence in learning
• Multimodal modeling of learner behavior (e.g., tutorial dialogue, clickstream, and language model interactions)
• Learning analytics, educational data mining, and AI in K-12 and higher education

Track B: AI-Supported Tutoring and Goal Setting

• Computational models of tutoring effectiveness and instructional quality
• Adaptive goal setting and motivational interventions
• AI-supported tutoring and instructional decision-making
• Modeling tutor and learner behavior during tutoring interactions
• Randomized field experiments in tutoring and educational technology
• Learning analytics for large-scale tutoring programs
• Human-AI collaboration in technology-supported tutoring

The position offers substantial intellectual freedom and opportunities to co-develop new lines of inquiry. For additional context on the potential intellectual direction of the position, prospective applicants may read the in-press or published manuscripts below:

Theoretical and position papers

• https://dl.acm.org/doi/pdf/10.1145/3785022.3785057
• https://arxiv.org/abs/2604.13534

Empirical papers

• https://arxiv.org/abs/2605.08943
• https://arxiv.org/abs/2603.24535
• https://dl.acm.org/doi/pdf/10.1145/3576050.3576081

Additional research associated with PLUS Tutoring

• https://dl.acm.org/doi/pdf/10.1145/3785022.3785041
• https://link.springer.com/chapter/10.1007/978-3-031-98459-4_4
• See also: https://tutors.plus

Applicants may come from fields including but not limited to:

• Computer Science
• Learning Sciences
• Statistics
• Computational Social Science
• Educational Data Mining/Learning Analytics
• AI in Education
• Machine Learning
• Cognitive Science
• Quantitative Psychology
• Education

Responsibilities:

• Conduct independent and collaborative research
• Help shape the lab’s emerging research agenda
• Develop computational and statistical models using large-scale educational data
• Mentor graduate and undergraduate students as appropriate
• Contribute to open-source research infrastructure and reproducible workflows
• Participate in interdisciplinary collaborations across Vanderbilt and external partners

What We Offer:

• Significant intellectual autonomy
• Access to large-scale longitudinal educational datasets
• Extensive and multidisciplinary international research collaborations
• Support for publications, conference travel, and career development
• Opportunities to contribute to research funding applications and mentor students
• Significant intellectual autonomy and opportunities to shape the lab's research agenda

Required Qualifications

• Ph.D. completed by start date in a relevant field
• Strong quantitative or computational research background
• Evidence of research potential through publications, projects, or dissertation work
• Analytical programming experience (e.g., Python, R, or related tools)
• Strong communication and writing skills
• Interest in educational systems, learning, motivation, or human behavior

Preferred Qualifications

• Experience with sequential, longitudinal, or networked data
• Experience with machine learning or statistical inference
• Prior work using educational, behavioral, or institutional datasets
• Interest in theory-building through computational approaches
• Expertise in theories of human learning and motivation
• Experience collaborating across disciplines and with external stakeholders (e.g., educational technology vendors, higher education institutions, or K-12 institutions)

How to Apply:

Please submit:

• Cover letter describing research interests and fit
• Academic CV
• 1-3 representative paper or research samples
• Contact information for 2-4 academic references

Applications will be reviewed on a rolling basis until the position is filled.

For questions and to express interest, please contact:
Conrad Borchers
Vanderbilt University
c.borchers@vanderbilt.edu