Publisher
source

TU Darmstadt

Closing soon

PhD position in Mathematical Foundations of Deep Learning at TU Darmstadt TU Darmstadt in Germany

Degree Level

PhD

Field of study

Computer Science

Funding

Available

Deadline

Oct 22, 2026

Country flag

Country

Germany

University

TU Darmstadt

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

More information can be found here

Keywords

Computer Science
Deep Learning
Mathematics
Probability Theory
Python Programming
Linear Algebra
Artificial Neural Network
Random Matrix Theory
Optimisation
Generalizability
Statistics
Linear Stability

Suggested positions

About this position

TU Darmstadt in Germany is offering a PhD position in the mathematical foundations of deep learning, hosted by the Signal Theory and Statistical Learning group in the Department of Electrical Engineering and Information Technology.

The project is part of the Emmy Noether initiative “RMT4DL: Random Matrix Theory for Deep Learning”, which seeks theoretical insights into the behavior of large-scale neural networks. The research focus is on probability theory and random matrix theory, with the broader aim of understanding stability, generalization, and feature learning in modern deep learning systems.

This is a full-time PhD position at a leading German technical university. The post is well suited to candidates with a strong mathematical and computational background who are interested in foundational questions in machine learning theory and statistical learning.

Eligibility highlights include a Master’s degree or equivalent in mathematics, computer science, or a closely related discipline; strong preparation in probability, optimization, linear algebra, and machine learning theory; programming experience in Python; and, ideally, familiarity with deep learning tools such as PyTorch or JAX. Experience with random matrix theory is a plus. Excellent English and the ability to work independently are also emphasized.

The application deadline is 22 October 2026 at 12:00 (Europe/Berlin). Interested candidates should apply through the TU Darmstadt career portal. Further details are available on the vacancy page, and questions can be directed to Mariia Seleznova at [email protected].

Funding details

Available

What's required

Applicants should have an excellent university degree (Master’s or equivalent) in mathematics, computer science, or a closely related field. A strong mathematical background is expected, particularly in machine learning theory, probability theory, optimization, and linear algebra. Experience with random matrix theory is a plus, as is programming experience in Python and familiarity with deep learning frameworks such as PyTorch or JAX. Candidates should have excellent written and spoken English, strong analytical skills, and enthusiasm for independent research.

How to apply

Apply via the TU Darmstadt career page using the provided job link. Review the full vacancy details and submit your application materials before 22 October 2026 at 12:00 (Europe/Berlin). For questions about the position, contact Mariia Seleznova by email.

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?