Postdoctoral Research Associate in Deep Learning

Corehr; Oxford; On-site; GBP 34,000 - 42,000; Full time

Job summary

The University of Oxford invites applications for a Postdoctoral Research Associate in Deep Learning to work with Professor Justin Sirignano in the Mathematical Institute. This is a 6-month fixed-term appointment funded by an EPSRC grant, with a start around 1 December 2026 and end around 31 May 2027, subject to approvals.

You will join the Machine Learning & Data Science group and contribute to the NSF-EPSRC project on asymptotic analysis of online training algorithms, collaborating with Oxford

Responsibilities

• Conduct research on the mathematical theory of deep learning as part of the joint NSF-EPSRC project.
• Develop rigorous proofs for convergence and asymptotic analysis of deep learning models.
• Collaborate in preparing research publications and present findings to the group.
• Contribute a small amount of teaching to the department (up to three hours a week).

Skills

Deep learning theory

Mathematical analysis

Probability

Stochastic analysis

Partial differential equations

Machine learning

Job description

Postdoctoral Research Associate in Deep Learning

We are currently inviting applications for a Postdoctoral Research Associate in Deep Learning to work with Professor Justin Sirignano at the Mathematical Institute, University of Oxford. This is a 6-month, fixed-term position funded by an EPSRC grant. We anticipate a starting date of 1 December 2026 (or as soon as possible thereafter) and an expected end date of 31 May 2027. There is scope for flexibility in the start and end dates, subject to approval by the department and the funding agencies.

The successful candidate will join the Machine Learning & Data Science research group and conduct research on the mathematical theory of deep learning as part of the joint NSF-EPSRC project “DMS-EPSRC: Asymptotic Analysis of Online Training Algorithms in Machine Learning: Recurrent, Graphical, and Deep Neural Networks”. The research will involve collaboration with Professor Justin Sirignano at Oxford and Professor Konstantinos Spiliopoulos at Boston University. The project develops new mathematical theory for training algorithms and neural network models, drawing on probability, partial differential equations, large deviations, stochastic analysis, optimisation and machine learning.

The successful candidate will contribute to the activities of the Machine Learning & Data Science research group, develop rigorous mathematical proofs for convergence and asymptotic analysis of deep learning models, methods and algorithms, and collaborate in the preparation of research publications. There will be opportunities to contribute a small amount of teaching to the department, of at most three hours a week during the academic terms.

We proudly hold a departmental Athena SWAN Silver Award and an institutional Race Equality Charter Bronze Award.

Please direct informal enquiries to the HR Administrator (email: [e-mail]), quoting vacancy reference 188574.

Only applications received before 12.00 noon UK time on 30 September can be considered.