The University of Rostock offers a diverse, varied and challenging position in a tradition-conscious, yet innovative, modern and family-friendly university in a lively city by the sea.
At the Faculty of Computer Science and Electrical Engineering, Institute for Visual and Analytic Computing, subject to allocation of funds, we are filling the following two positions at the earliest possible date on a temporary basis for the duration of the project NEXCELL ending on 31.12.2028:
Research Assistants (Postdocs) (m/f/d) - AI
Start date at the earliest possible date
Working hours full-time with 40 hours
Remuneration pay group 13 TV-L
Location Rostock
Tender number P 14/2026
Limitation limited until 31.12.2028
Application time 2026-02-22
Please do not hesitate to contact us for further information:
HR department:
Pia-Lucy Dahl
Phone number: 0381/498-1291
E-mail:
Department:
Prof. Thomas Kirste
Phone number: 0381/498-7510
E-mail:
The project addresses fundamental and applied challenges at the intersection of machine learning, probabilistic modeling, symbolic AI, and bioprocess engineering, with strong relevance to both academic research and industrial innovation. The positions offer a clearly defined pathway toward postdoctoral qualification, as well as structured opportunities for career development in academia and industry.
NEXCELL is a major multi-million-€ collaborative research initiative that brings together leading industrial and academic partners to create a groundbreaking point-of-care platform for next-generation cell and gene therapies. The vision is to enable personalized cancer treatments to be manufactured directly at the clinical site – making life-saving therapies more accessible and scalable. Within this project, the University of Rostock serves as the AI technology provider, developing a probabilistic digital twin of the NEXCELL bioreactor system. This digital twin will combine Bayesian AI, deep learning, symbolic reasoning, and hybrid modeling techniques to intelligently monitor and predict both technical and biological processes. By addressing challenges such as uncertainty quantification, multimodal sensor fusion, anomaly detection, and robust state estimation, our research will push the frontiers of AI in complex, safety-critical, and data-sparse domains. For motivated AI researchers, NEXCELL offers a unique opportunity to conduct fundamental research at the interface of cutting-edge machine learning and real-world bioprocess applications, with the potential for high-impact publications, open-source contributions, and direct collaboration with a market leader in bioreactor technology.
We invite two outstanding postdoctoral researchers to join our institute in collaboration with a global industrial leader in bioreactor technology. The successful candidates will contribute to a large-scale, interdisciplinary research project focused on the development and deployment of advanced artificial intelligence methods for system monitoring, state estimation, and decision support in next-generation bioreactor platforms.
Application Documents and Procedure
Applications must be submitted in complete form and include all required formal documents, in particular:
- a curriculum vitae,
- certificates and transcripts of academic degrees,
- proof of language proficiency.
Applicants must further submit a cover letter in which they explicitly address and document compliance with eligibility criteria (1)–(6) ("this makes you a good fit").
Incomplete applications or applications not meeting the eligibility criteria may not be considered.
After submission, the application process is multi-staged and will include analytical tasks as part of the selection procedure.
THESE ARE YOUR TASKS:
- design, implement, and evaluate deep neural, probabilistic, and hybrid symbolic-learning models for real-time sensor fusion, anomaly detection, and latent state estimation in dynamic bioreactor environments
- adapt and extend large language models (LLMs) and symbolic reasoning frameworks to interpret domain-specific process logs, develop predictive diagnostics, and support explainable and trustworthy decision-making pipelines for bioprocess engineers
- develop multi-modal bioinformatics pipelines for temporal single-cell analysis based on longitudinal pattern mining, geometric and graph deep learning
- collaborate closely with industrial partners and domain experts to curate multimodal process data, design and execute validation experiments, perform simulation studies, and iteratively refine models for deployment in real-world bioprocess settings
- investigate reinforcement learning, simulator-based inference, and adaptive control strategies for feedback control and trajectory tracking in bioprocesses characterized by high uncertainty and complex nonlinear dynamics
- contribute to high-impact, open scientific research, including the development of open-source software tools, co-authorship of peer-reviewed conference and journal publications, presentation of results at international venues, and supervision or mentoring of junior students, thereby establishing a strong and visible scientific profile
THIS MAKES YOU A GOOD FIT:
- academic qualifications:
- completed bachelor's and master’s degree in Computer Science, or a diploma in Computer Science or a comparative course of study with a predominantly computer science curriculum
- the qualifying degree must have been completed with a grade 1.7 or better (German grading system)
- degree must have been awarded by a higher education institution (recognized as H+ according to the German Anabin system)
- completed doctoral degree in Computer Science awarded with a final grade of magna cum laude or higher
- language proficiency: applicants must meet either of the following language profiles:
- proficiency in written and spoken English at level C1 CEFR (e.g. IELTS overall score ≥ 7.0, or TOEFL ≥ 94); or
- native-level proficiency in German and demonstrated English language skill
- research experience:
- documented experience in artificial intelligence, statistical / probabilistic modeling and/or data analysis is required
- demonstrated analytical skillset, ability to solve novel and complex tasks independently and present results coherently
- organizational and time-management skills: demonstrated ability to work independently and reliably under time constraints and to meet deadlines
- communication skills: proven ability to communicate scientific results effectively, both orally and in written form
- interdisciplinary competence: demonstrated ability to work collaboratively in interdisciplinary research environments
WE AS AN EMPLOYER:
Equal opportunities are important to us. We welcome applications from suitable severely disabled people or people from traditionally underrepresented groups. We aim to increase the proportion of women in research and teaching and therefore encourage suitably qualified women to apply. We welcome applications from people of other nationalities or with a migration background.
WE OFFER YOU:
FURTHER INFORMATION:
We will determine the experience level individually, taking into account your previous professional experience.
If you would like to work part-time in this position, this is possible subject to the requirements of the position.
The temporal limitation of the employment relationship is based on § 2 (2) Wissenschaftszeitvertragsgesetz.
We look forward to receiving your application (cover letter, CV, degree certificate stating your final grade) by 22.02.2026 at the latest. We can only consider applications received via our homepage. Please send us your documents via the ‘Online application’ button at the end of a job offer. Unfortunately, we cannot accept e-mail applications.
Incomplete application documents may not be considered in the further course of the selection process.
Unfortunately, we can not cover application and travel costs.
Become part of the team
The Hybrid Methods in Artificial Intelligence and Machine Learning group is part of the Institute for Visual & Analytic Computing at the Faculty of Computer Science and Electrical Engineering at the University of Rostock. Its research focuses on the integration of symbolic, probabilistic, and neural approaches in AI & ML. The application domains include AI-supported digital twins, intelligent environments, situation-aware assistance, and multimodal diagnostics. The methodological focus is on sequential state estimation using hybrid Bayesian and neuro-symbolic models, as well as the integration of deep learning with symbolic background knowledge. The positions are co-supervised by Hessian.AI group leader Martin Becker (Marburg University) focusing on knowledge-centric AI and biomedical ML with a strong international network.
We look forward to receiving your application!
Contact
Universität Rostock
18051 Rostock
Tel.: +49 381 498 - 0
Sitze des Rektorats:
Universitätsplatz 1
18055 Rostock
Service
lity
Certificates
Familienfreundliche Hochschule HRK-Audit