"Postdoctoral Research Associate"

Job Identification

11030

UE07: £39,347.00 - £46,794.00 Per Annum.

College of Science & Engineering / School of Mathematics.   

Fixed Term Contract - 36 months.

Full Time - 35 Hours Per Week.

We are looking for a talented early career researcher in fluid dynamics and/or machine learning, with expertise in computational methods to work on the project “A new understanding of turbulence via a machine-learnt dynamical systems theory” (UKRI Frontier Research Guarantee for an ERC Starting Grant). 

The Opportunity:

The dynamical systems view of turbulence, in which the flow “pinballs” between exact coherent states (ECS), is a promising way to unify our statistical understanding of turbulence with a mechanistic understanding of the complex self-sustaining processes that underpin it. Historically, this approach has been restricted to weakly turbulent flows due to the difficulty of identifying and converging ECS, and this project will seek to use advances in machine learning and automatic differentiation to overcome these barriers. 

A core part of this project is the development and interpretation of state-of-the-art machine learning (ML) models to model and predict high Reynolds number fluid flows. This will be the focus of this particular postdoc, where the post-holder will work on a combination of: (1) low order models for high-dimensional flows, e.g. generated via self-supervised learning, to parameterise the inertial manifold; (2) super-resolution/data-assimilation strategies incorporating the flow solver in the loss; (3) the application of interpretability techniques to attempt to reverse-engineer large ML models to extract latent learned physical concepts. The latter area is developing rapidly in the context of large language models but has not been explored in detail for physical problems. 

There are significant computational resources set aside specifically for the post-holder, along with PI, to train large models (access to a dedicated GPU cluster with ~160 A100/H100 cards). There is scope for a strong candidate to shape the research direction. 

Relevant reading:

• Page, Norgaard, Brenner & Kerswell, “Recurrent flow patterns as a basis for turbulence: predicting statistics from structures”, Proceedings of the National Academy of Sciences 121 (2024)
• Templeton, et al., “Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet”, Transformer Circuits Thread (2024)
• Kochkov et al, “Machine learning-accelerated computational fluid dynamics”, Proc. Nat. Acad. Sci. 118 (2021)

Your skills and attributes for success:

• Excellent knowledge of fluid mechanics fundamentals 
• Experience implementing machine learning approaches and/or high performance computing for flow simulations (Desirable).
• Strong coding skills in an object-oriented language
• Experience with machine learning libraries (e.g. one or more of JAX, TensorFlow, PyTorch) would be highly beneficial (Desirable).

Click to view a copy of the full job description (opens new browser tab) 

Applicants should upload a CV and a brief research statement (max two pages) when applying for the post online. In addition, they should arrange for at least two letters of reference to be sent direct to references@maths.ed.ac.uk quoting the reference number 11030. For informal enquiries please contact Jacob Page – jacob.page@ed.ac.uk

As a valued member of our team you can expect: 

Significant budget for international travel and computing resources, with opportunities to visit and collaborate with researchers and engineers from leading universities and technology companies. 

The University of Edinburgh is an exciting, positive, creative, challenging and rewarding place to work. We give you support, nurture your talent and reward success. You will benefit from a competitive reward package and a wide range of staff benefits, which includes a generous holiday entitlement, a defined benefits pension scheme, staff discounts, family-friendly initiatives, flexible working and much more. Click to access our staff benefits page (opens new browser tab) for further information and use our reward calculator to find out the total value of pay and benefits provided.

The University of Edinburgh holds a Silver Athena SWAN award in recognition of our commitment to advance gender equality in higher education. We are members of the Race Equality Charter and we are also Stonewall Scotland Diversity Champions, actively promoting LGBT equality. 

If invited for interview you will be required to evidence your right to work in the UK. Further information is available on our right to work webpages (opens new browser tab). This post is sponsorable for a skilled worker visa.

Unless stated otherwise the closing time for applications is 6th September 2024 at 11:59pm GMT. If you are applying outside the UK the closing time on our adverts automatically adjusts to your browsers local time zone. 

The University is able to sponsor the employment of international workers in this role. If successful, an international applicant requiring sponsorship to work in the UK will need to satisfy the UK Home Office’s English Language requirements and apply for and secure a Skilled Worker Visa.