to work on an interdisciplinary project to provide High Energy Physics (HEP) with robust deep density machine-learning (ML) tools with focus on predictive, generative and anomaly detection models, with the ultimate objective to maximise the LHC’s sensitivity to discover physics beyond the Standard Model. A particular focus rests on cutting-edge ML applied to jet flavour tagging. The applicants will have the opportunity to work alongside a large international community as members of the ATLAS collaboration, and bring the latest developments in ML to the collaboration.

The students will work within an interdisciplinary working group led by internationally recognised experts in their field:

The successful PhD candidates have (or soon receive) the equivalent of a Master degree with a specialisation in one or more of the areas of:

as well as outstanding grades.

The successful candidates will be co-supervised by Tobias Golling and Slava Voloshynovskiy and have the opportunity to be part of and shape this interdisciplinary project spanning all the way from the development of theoretical ML foundations to their practical applications and generalisation in real-world science questions in the above-mentioned domains.

Doctoral candidates will normally complete their doctoral requirements within 4 years, however, extensions up to a 5th year are possible. The post includes teaching duties and supervision of undergraduate students, as well as opportunities for outreach work. Non-francophone candidates are encouraged to achieve proficiency in French during their first year of studies.

To apply please

Applications should be received by September 30 2021 and the position is expected to start by January 2022 (or earlier). For further information please contact Tobias.Golling@unige.ch.