Postdoctoral Researcher in Diagrammatic Probabilistic First-order Logic for Safeguarding AI

The Department of Software Science invites applications for a postdoctoral researcher position in Diagrammatic Probabilistic First-order Logic for Safeguarding AI.

The goals of the position are to:

• perform high-level collaborative research in a team led by Prof Pawel Sobocinski;
• disseminate research results in top-tier conferences and journals;
• contribute to the ongoing research projects of the Estonian Center of Excellence in AI (EXAI);
• help to supervise graduate students in the Laboratory for Compositional Systems and Methods and
• the opportunity to contribute to teaching at undergraduate and postgraduate level.

CONTEXT:

The successful candidate will (i) participate in the activities of the Estonian Center of Excellence in AI and be actively involved it its ongoing research projects and (ii) work with a team in the Compositionality group at TalTech to introduce a combinatorial, programmatic, and diagrammatic syntax for probabilistic logic.

First-order logic has a recent string diagrammatic complete axiomatisation [1] in terms of first-order bicategories. At the same time, the morphisms of the Kleisli category of the finitary subdistribution monad have posetal structure given by a point-wise ordering. This structure is similar to the one of the regular fragment of first- order bicategories.

These observations point towards an extension of partial Markov categories [2] to a probabilistic analogue of cartesian bicategories of relations and first-order bicategories, with potentially richer 2-cells. Such structure could be further developed to incorporate traces, which would give a syntax for deriving statements for probabilistic processes analogous to Hoare triples for non-deterministic processes.

We intend this work to be a step towards an expressive formalism for the specification and reasoning about probabilistic systems, including systems that include AI compoments.

1. Filippo Bonchi, Alessandro Di Giorgio, Nathan Haydon, and Pawel Sobocinski. Diagrammatic algebra of first order logic. In 2023 39th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS). ACM, 2024.

2. Elena Di Lavore and Mario Román. Evidential decision theory via partial Markov categories. In 2023 38th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS), pages 1–14. IEEE, 2023.

Contact person: Pawel Sobocinski pawel.sobocinski@taltech.ee.

PhD in computer science, mathematics or a closely related field.

• is motivated to perform interdisciplinary research with focus on applications in AI; 
• desirable: has experience in string diagrammatic approaches to logic and/or probability theory; 
• desirable: has experience of probabilistic verification, e.g. probabilistic model checking;
• desirable: has an understanding of generative AI foundation model architectures, e.g. GANs and/or transformers.

To apply for the position, please send the following documents in English by 15 August 2024 at the latest by clicking the application link "Apply Now":

• a motivation letter; 
• documents proving that the candidate holds the required academic degree for the position applied; 
• a CV, including a list of publications;
• an academic portfolio, including a motivated self-evaluation regarding compliance with the requirements for the researcher position set out in the Academic Career Management Regulation, Annex 3 “Academic Evaluation Matrix” (shall be submitted by a university staff member only) or a free format evaluation of the academic activity undertaken so far and the competencies required for work (shall be submitted by an external candidate only) detailing how the candidate meets the qualifications of the position; 
• other documents considered important by the candidate.

Regarding further information on the application documents and recruitment process please contact TalTech HR konkurss@taltech.ee.

Tallinn University of Technology (TalTech) is the flagship in engineering and IT science and education in Estonia, providing higher education at all levels in engineering and technology, information technology, economics, science, and maritime. TalTech’s mission is to be a promoter of science, technology, and innovation and a leading provider of engineering and economic education in Estonia. The university has over 2000 employees and over 10 000 students, and approximately 70 000 alumni.

The Compositional Methods and Systems group focusses on harnessing compositional techniques to improve software trustworthiness in several application areas, including concurrency theory, quantum programming and AI safety and trustworthiness.

TalTech has a green and one of the most compact university campuses in Europe that includes the Tehnopol Tallinn Science Park. Low hierarchy, academic freedom and a balanced work and family life are valued at TalTech. The university provides individual development and training opportunities, material and non-material tokens of acknowledgement, sporting opportunities at TalTech Sports Club and all-staff activities.