We are looking for people with computer science (or related) background interested in trustworthy machine learning research. We offer fully-funded PhD/PostDoc positions on one or more of the following topics: adversarial robustness (attacks, defenses, certificates), privacy attacks and privacy-preserving learning, algorithmic fairness and bias, uncertainty-aware models, out-of-distribution detection, out-of-domain generalization, and explainability. If you are interested in working with us on these (or adjacent) topics keep reading. One focus area is on graph-based models such as graph neural networks which have emerged as a fundamental building block in many AI systems.
- A Master (or equivalent) degree in Computer Science or a closely related field
- Knowledge of at least one programming language (preferably Python)
- Background in machine learning and/or data mining is a plus
- Solid mathematical foundation (e.g. probability theory, statistics, calculus, and linear algebra) is a plus
- Experience with frameworks such as PyTorch, TensorFlow, or similar is a plus
- For PostDocs: PhD in a closely related area and publications at the following venues: ICML, NeurIPS, ICLR, KDD, WWW, AAAI, AISTATS
The positions include full benefits and are paid very well according to the collective labor agreement TVöD: 100% E13 for PhDs (around 4K euros per month before taxes) and 100% E14 for PostDocs (around 4.5K euros per month before taxes).
How to apply
Please send your application (as a single PDF file, no external links) to Aleksandar Bojchevski via email using the subject line
The application should include:
- Transcripts of records
- Abstract of your master thesis (and PhD thesis if you are applying for a PostDoc)
- List of publications (if available)
We welcome applications regardless of gender, nationality, ethnic and social origin, religion/belief, disability, age, and sexual orientation. Applications will be considered as they arrive and until the positions are filled. There is no deadline. The starting date is flexible, sooner is better. Don’t hesitate to get in touch if you have any questions.