PhD Position in Privacy-Preserving and Reliable Artificial Intelligence

01.09.2022, Wissenschaftliches Personal

The Trustworthy and Privacy-Preserving AI Group at the Institute for AI in Medicine is offering a PhD candidate position (TV-L E13, 100% for 3 years) in Privacy-Preserving and Reliable Artificial Intelligence to be occupied starting from the 01.10.2022.

The Trustworthy and Privacy-Preserving AI Group (PI: PD Dr. Georgios Kaissis) at the Institute for AI in Medicine (Director: Prof. Dr. Daniel Rueckert) is seeking to fill PhD candidate position (TV-L E13, 100% for 3 years) in Privacy-Preserving and Reliable Artificial Intelligence to be occupied starting from the 01.10.2022.

Your Responsibilities: You will work at the cutting edge of privacy-preserving deep learning research with a focus on one or more of the following topics: - Optimal model design for differentially private machine learning: Differential privacy (DP) is the gold-standard for privacy protection, but deep learning models trained with DP suffer from privacy-utility trade-offs. You will develop novel model architectures which leverage our increasing understanding of the behaviour of neural networks trained with DP to ameliorate these trade-offs in biomedical applications. - Foundations of private machine learning: You will study the effects of privacy-preserving machine learning on memorisation, fairness, interpretability and model uncertainty utilising techniques from information theory and quantitative information flow. Understanding these attributes is critical for the responsible application of such models to medical settings.

Your Qualifications: - Holding an excellent MSc in the field of pure or applied mathematics, (theoretical) computer science, machine learning foundations, electrical engineering, information theory, cryptography, statistics or a related field. - Advanced knowledge of probability theory, information theory, statistics, real/functional analysis, statistics. - Excellent programming and software engineering skills at least in Python and in relevant machine learning libraries (at least one of: Pytorch, TensorFlow, JAX) demonstrable through a relevant portfolio. - Excellent language skills in English. German language skills are desirable but not required.

We are offering: - An interdisciplinary, diverse young team of researchers working at the intersection of privacy-preserving machine learning, advanced artificial intelligence and medical applications - An inclusive, open research climate with excellent collaboration opportunities and the possibility to contribute your own ideas and work on topics which truly excite you - Access to advanced computational resources and an excellently equipped workplace - Opportunities for international collaboration

Please send your cover letter, CV and transcript of records to the email address below. It must be clear from your cover letter and/or transcript why you wish to conduct research in privacy-preserving machine learning in particular and why and to what extent you feel you are qualified for the position. Applications which do not fulfil this requirement will be rejected without consideration.

Notice for candidates with disabilities:

Schwerbehinderte werden bei im Wesentlichen gleicher Eignung und Qualifikation bevorzugt eingestellt. Candidates with disabilities will be given preference if they are essentially of the same suitability and qualifications.

The position is suitable for disabled persons. Disabled applicants will be given preference in case of generally equivalent suitability, aptitude and professional performance.

Data Protection Information:
When you apply for a position with the Technical University of Munich (TUM), you are submitting personal information. With regard to personal information, please take note of the Datenschutzhinweise gemäß Art. 13 Datenschutz-Grundverordnung (DSGVO) zur Erhebung und Verarbeitung von personenbezogenen Daten im Rahmen Ihrer Bewerbung. (data protection information on collecting and processing personal data contained in your application in accordance with Art. 13 of the General Data Protection Regulation (GDPR)). By submitting your application, you confirm that you have acknowledged the above data protection information of TUM.

Kontakt: [email protected]