Publisher
source

Konrad Rieck

Just Landed

Posted Yesterday

Fully Funded PhD Position in Adversarial Mechanistic Interpretability Technische Universität Berlin in Germany

Degree Level

PhD, Postdoc

Field of study

Computer Science

Funding

The PhD position is fully funded. No stipend amount or additional funding details are provided in the post.

Deadline

Nov 26, 2026

Country flag

Country

Germany

University

Technische Universität Berlin

Apply for this position

Free with an ApplyKite account: the application link, the deadline in your tracker and a check of your fit.

Keywords

Computer Science
Artificial Intelligence
Explainable Ai
Interpretability

More like this

Suggested positions

Publisher
source

TU Darmstadt

Country flag

Germany

TU Darmstadt’s Artificial Intelligence Hardware research group is recruiting a research associate and PhD candidate to work at the interface of AI hardware and AI algorithms. The doctoral research will focus on the development of efficient AI hardware and AI systems, with potential topics including efficient AI hardware architectures, hardware-software co-design for efficient AI systems, and hardware-aware AI algorithms. The group also works on energy-efficient AI algorithms, explainable AI, and...

Computer Science
Electrical Engineering
Artificial Intelligence
+1 more

1 days ago

Publisher
source

Gitta Kutyniok

Ludwig-Maximilians-Universität München

Country flag

Germany

Ludwig-Maximilians-Universität München invites applications for a PhD or postdoctoral position in the Chair for Mathematical Foundations of Artificial Intelligence (MATH4AI), led by Prof. Dr. Gitta Kutyniok at the Mathematical Institute. The position is located in Munich and is connected to an international research team working at the interface of mathematics and artificial intelligence. The researcher will join the project “Spiking Neural Networks: Theoretical Foundations, Trustworthiness, and...

Computer Science
Deep Learning
Mathematics
+4 more

1 week ago

Publisher
source

University of Potsdam

Country flag

Germany

The Research School “Foundations of AI” is a doctoral programme offered by the Hasso Plattner Institute in cooperation with the Faculty of Digital Engineering, a faculty jointly founded by HPI and the University of Potsdam. It is based in Potsdam and embedded in an environment focused on computer science and digital technologies. The programme is centred on foundational artificial intelligence research. Doctoral researchers work on advancing AI methods, with an emphasis on energy-efficient and p...

Computer Science
Information Technology
Mathematics
+5 more

1 week ago

Publisher
source

Matthias Niessner

Technical University of Munich

Country flag

Germany

Technical University Munich's Visual Computing & AI Lab in Munich is recruiting fully funded PhD and postdoctoral researchers for cutting-edge work in artificial intelligence. Research topics include Generative AI , agentic 3D understanding, 3D Gaussian Splatting (3DGS), diffusion models, world models, and related visual computing areas. The positions are based in Munich, Germany, and are funded through TV-L E13 employment at 100%. The post does not specify individual eligibility requirements or...

Computer Science
Artificial Intelligence
Computer Vision
+1 more

2 weeks ago

Publisher
source

Steffen Staab

University of Stuttgart

Country flag

Germany

The Analytic Computing group at the University of Stuttgart is inviting applications for three PhD student / doctoral researcher positions and one postdoctoral position . Research topics include knowledge graphs , agentic AI , foundation models , and the interpretation and prediction of human attention during interaction and collaboration. This is a strong fit for candidates interested in computer science , information technology , and related areas such as cognitive science and psychology . Doc...

Computer Science
Psychology
Cognitive Science
+2 more

1 month ago

About this position

Technische Universität Berlin’s Chair of Machine Learning and Security is offering a fully funded PhD position focused on adversarial mechanistic interpretability.

The project investigates how explanations produced by machine-learning models can be manipulated or “gamed,” and how interpretability methods can be designed to provide more trustworthy insight into model behavior. The research addresses the reliability of explanations as an output channel and connects mechanistic interpretability with machine learning security and trustworthy artificial intelligence.

The successful researcher will join the Machine Learning and Security research group led by Professor Konrad Rieck at TU Berlin. The group also advertises opportunities for PhD students and postdocs, providing a research environment centered on machine learning, security, and the analysis of modern AI systems.

Funding details

The PhD position is fully funded. No stipend amount or additional funding details are provided in the post.

How to apply

Review the opening and application instructions on the Machine Learning and Security group’s jobs page at mlsec.org/jobs.html#jobs. Submit the required application materials according to the instructions before November 26, 2026.

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts and confirm requirements with the university.

Professors

Professor

University Name
Country flag

Germany

Research Interests

Artificial Intelligence

Cybersecurity

Machine Learning

Computer Science

Malware Analysis