Post doctor (2 years) within machine learning for continuous and discrete structures title - Befattningen är under tillsättning eller redan tillsatt, och det är inte längre möjligt att lämna in en ansökan

The Department of Computing science seeks a postdoctor to join the project STING - Synthesis and analysis with Transducers and Invertible Neural Generators. The employment is full-time for two years with access January 7, 2025, or by agreement.

Department of Computing science

The Department of Computing Science is characterized by world-leading research in a multitude of scientific fields, and is ranked highly in international comparison. The department has been growing rapidly in recent years, with a focus on creating an inclusive and bottom-up driven research environment. To further strengthen our numbers, we are now looking for a postdoctor in machine learning for continuous and discrete structures. Our workplace consists of a diverse set of people from different nationalities, background and fields. If you work as a postdoctor with us, you receive the benefits of support in career development, networking, administrative and technical support functions, along with good employment conditions. More information about the department is available at: Department of computing science

Is this interesting for you? Welcome with your application before November 12, 2025

Project description and working tasks

Wallenberg AI, Autonomous Systems and Software Program (WASP) is Sweden’s largest individual research program ever, a major national initiative for strategically motivated basic research, education and faculty recruitment. The program addresses research on artificial intelligence and autonomous systems acting in collaboration with humans, adapting to their environment through sensors, information and knowledge, and forming intelligent systems-of-systems.  The vision of WASP is excellent research and competence in artificial intelligence, autonomous systems and software for the benefit of Swedish society and industry. Read more: https://wasp-sweden.org/ 

Human communication is multimodal in nature, and occurs through combinations of speech, language, gesture, facial expression, and similar signals. STING aims to design models that capture this richness, uniting synthesis and analysis with the help of transducers and deep neural generative models. This involves connecting concrete, continuous valued sensory data such as images, sound, and motion, with high-level, predominantly discrete, representations of meaning, which has the potential to endow synthesis output with human understandable high-level explanations, while simultaneously improving the ability to attach probabilities to semantic representations. The bidirectionality also allows us to create efficient mechanisms for explainability, and to inspect and enforce fairness in the models.

The partner research groups bring complementary expertise to the project: KTH has extensive experience with probabilistic deep learning for analysis and synthesis of human verbal and nonverbal communication. Umeå University, on the other hand, are experts on transducer and grammar models for generating semantic graphs, and have recently started to apply these to the task of parsing multimodal data. They also contribute experience with bias analysis and mitigation. Linköping University complements these aspects with in-depth knowledge of natural language processing, language being a discrete yet observable signal modality of great interest for bridging the two ends of the project.

In addition to its scientific value, the project is expected to have a substantial societal imprint. The resulting technologies may, e.g., be used to create virtual patients for medical training, to model non-playable characters in video games, and to derive affective states and underlying health issues from human speech and nonverbal behaviour. Read more about the NEST project at:

https://wasp-sweden.org/sting-synthesis-and-analysis-with-transducers-and-invertible-neural-generators/

Possible research directions for the postdoctor are:

• Work on the latest deep generative models with diffusion models and normalising flows
• Combining discrete and continuous methods for synthesis and/or analysis

The project is conducted within the research group for the Foundations of Language Processing at Umeå University. The group studies theoretical and practical aspects of representing language on computers, and its interconnection with other sources of information. The work of the group spans from formal language theory to applied natural language processing. The group consists of five senior researchers and five PhD students. More information is available at:

https://www.umu.se/en/research/groups/foundations-of-language-processing/

Qualifications

To be appointed under the postdoctoral agreement, the postdoctoral fellow is required to have completed a doctoral degree or a foreign degree deemed equivalent to a doctoral degree. These qualification requirements must be fulfilled no later than at the time of the appointment decision.

To be appointed under the postdoctoral agreement, priority should be given to candidates who completed their doctoral degree, according to what is stipulated in the paragraph above, no later than three years prior. If there are special reasons, candidates who completed their doctoral degree prior to that may also be eligible. Special reasons include absence due to illness, parental leave, appointments of trust in trade union organisations, military service, or similar circumstances, as well as clinical practice or other forms of appointment/assignment relevant to the subject area. Postdoctoral fellows who are to teach or supervise must have taken relevant courses in teaching and learning in higher education.

The postdoctor must have extensive experience in at least one of

• Formal language theory
• Machine learning

Other desirable qualifications include experience of

• Natural language processing
• Formal graph languages
• Graph representation learning
• Empirical methods, i.e., formal hypothesis testing

Application

A full application should include:

• Cover letter in which you explain why you are interested in the research project and how you think you could contribute,
• Curriculum vitae (CV) with publication list,
• Verified copy of doctoral degree certificate or documentation that clarifies when the degree of doctor is expected to be obtained,
• Copy of doctoral thesis and, optionally, up to 3 relevant articles, Other documents the applicant wishes to claim,
• Contact information to two persons willing to act as references.

The application must be written in English or Swedish. The application is made through our electronic recruitment system. Documents sent electronically must be in Word or PDF format. Log in to the system and apply via the button at the end of this page. The closing date is November 12, 2025.

Further details are provided by Johanna Björklund (johanna@cs.umu.se, Umeå University), Henrik Björklund (henrikb@cs.umu.se, Umeå University), and Frank Drewes (drewes@cs.umu.se, Umeå University)