Postdoctoral Researcher (m/f/d) in Topological Data Analysis for Deep Learning
The Department of Computer Science (Dialogue Systems and Machine Learning) at Heinrich Heine University Dusseldorf investigates fundamental questions in human–computer interaction, at the intersection of Natural Language Processing and Machine Learning. The research focuses on building intelligent dialogue systems that can learn, reason, adapt, and interact effectively with humans in dynamic and uncertain environments. The group develops principled methods for dialogue modelling, representation learning, reinforcement learning, knowledge acquisition, and user simulation.
Main Tasks
Investigate Topological Data Analysis (TDA) and its applications to deep learning, natural language processing, and representation learning
Focus on understanding whether topological and geometric properties of neural representations can provide interpretable signatures of learning dynamics and important machine learning phenomena
Develop and apply topological methods, design and conduct computational experiments, and publish research in leading venues
Work in an interdisciplinary research environment spanning mathematics, machine learning, and NLP, as a member of the Dialogue Systems and Machine Learning group (led by Prof. Milica Gašić) and jointly advised by Prof. Marcus Zibrowius from the Topology and Geometry group
Your Profile
Completed scientific university education (M.Sc./M.A./Diploma/Magister) in Mathematics, Computer Science, or a related field
PhD in Mathematics, Computer Science, or a related field (or close to obtaining)
Desirable: strong publication record
Desirable: experience in one or more of the following areas:
Topological data analysis
Machine learning
Deep learning or natural language processing
Essential: excellent written and oral communication skills in English, strong programming skills, and the ability to work collaboratively
Desirable: the ability to teach in German
Our Offer
Full-time position with a competitive salary (EG 13 TV-L) and 4 SWS of teaching duties in relevant courses
Opportunity to contribute to cutting-edge research at the intersection of topological data analysis, machine learning, and natural language processing
Position initially fixed-term for one year, with the possibility of extension for a further three years, subject to satisfactory performance
Qualification position under the Act on Temporary Scientific Contracts (Wissenschaftszeitvertragsgesetz, WissZeitVG)
Negotiable start date, with 1 January 2027 or earlier preferred
Benefits:
Company pension grant
Good transport connection
Free parking
International work
Bonus payments
Union rates
Payment of capital-forming benefits
Heinrich Heine University upholds the principle of "Excellence through Diversity" . It has signed the "Diversity Charter" and successfully participated in the Stifterverband's audit "Shaping Diversity" . It is certified as a family-friendly university and promotes diversity among its staff. Applications from people of all genders are expressly welcome. Applications from women will be given preferential consideration in accordance with the State Equal Opportunities Act. The application of severely disabled persons and persons with equivalent disabilities is also welcome.
Job description automatically summarized using AI