PhD student in Computing Science with focus on Machine Learning for Graph Transformations

Umeå University is offering a PhD position in Computing Science with a focus on machine learning for graph transformations. The project investigates a hybrid approach that combines deep learning with grammatical inference to develop models that are interpretable, efficient, and mathematically verifiable while leveraging the flexibility of neural methods. If successful, the work has the potential to advance applications such as automated theorem proving, knowledge-graph inference, and causal analysis.

The Department of Computing Science has experienced rapid growth in recent years, with a strong emphasis on fostering an inclusive, collaborative, and bottom-up-driven research environment. Our workplace brings together a diverse community of individuals from a wide range of nationalities.

As a PhD student with us, you benefit from comprehensive career development support, opportunities for networking, and access to robust administrative and technical services—all within a setting that offers attractive employment conditions.

To learn more about the department, please visit: https://www.umu.se/en/department-of-computing-science/

Project description

Graphs are a fundamental way of representing structured information from sentences and computer programs to social networks and they are becoming increasingly important as generative AI systems move beyond text. To keep such systems safe and reliable, we need mechanisms that can ensure their outputs follow the right rules, much like guardrails that prevent language models from producing harmful content or incorrect code. This project introduces a new idea: instead of relying on opaque, heavy machine-learning models, it learns transparent, rule-based rewriting systems that can transform graphs, check the correctness of AI-generated structures, and even guide neural networks during inference. By combining techniques from grammatical inference, reinforcement learning, and efficient search algorithms, the method can automatically discover both the rules and probabilities needed to model complex graph behaviors, offering a more interpretable and verifiable alternative for future AI systems.

The student will collaborate closely with the PI and her research group at Umeå University to investigate the proposed learning approach. The PhD student is expected to produce research outputs relevant to the fields of theoretical computer science and symbolic machine learning.

Admission requirements

The general admission requirements for doctoral studies are a second- cycle level degree, or completed course requirements of at least 240 ECTS credits, of which at least 60 ECTS credits are at second-cycle level, or have an equivalent education from abroad, or equivalent qualifications.

To be admitted to doctoral studies in the field of computer science, the applicant must have completed courses totaling at least 90 higher education credits in computer science or in subjects directly relevant to the specific specialization.

Requirements

We are looking for candidates who have:

Solid analytical and mathematical abilities Experience with machine learning Experience with formal language theory or automata theory Strong communication skills and proficiency in English The ability to work independently as well as collaboratively

Meritorious Qualifications

It is considered an advantage if you have:

Experience with academic writing Strong programming skills, particularly in Python Familiarity with knowledge graphs Experience with graph neural network

Personal Qualities

We value candidates who are:

Intellectually curious Self-motivated and well-organized Eager to engage with the scientific community

About the position

The position provides you with the opportunity to pursue PhD studies in Computing Science for four years, with the goal of achieving the degree of Doctor in Computing Science. While the position is mainly devoted to PhD studies (at least 80% of the time), it may include up to 20% department service (usually teaching). If so, the total time for the position is extended accordingly, resulting in a maximum of five years.

The procedure for recruitment for the position is in accordance with the Higher Education Ordinance (chapter 12, 2§) and the decision regarding the position cannot be appealed.

The expected starting date is April 1, 2026 or as otherwise agreed.

Application

Applications must be submitted electronically using the e-recruitment system of Umeå University.

A complete application should contain the following documents:

A cover letter including a description of your research interests, your reasons to apply for the position, and your contact information A curriculum vitae Reprints / copies of completed BSc and/or MSc theses and other relevant publications, if any Copies of degree certificates, including documentation of completed academic courses and obtained grades Documentation and description of other relevant experiences or competences.

The application must be written in English or Swedish. Attached documents must be in pdf format. Applications must be submitted electronically using the e-recruitment system of Umeå University, and be received no later than Feb 6, 2026.

The Department of Computing Science values gender diversity, and therefore particularly encourages women and those outside the gender binary to apply for the position.

For additional information, please contact Professor Johanna Björklund (email: johanna@cs.umu.se).