Job Description

Grade UE07: 41,064- 48,822 per annum

Science and Engineering / School of Informatics

Full-time: 35 hours per week

Fixed term: 2 years, until 31 December 2027

The Opportunity:

The School of Informatics, University of Edinburgh invites applications for a 2-year Post-Doctoral Research Associate (PDRA) to do research on efficient methods for foundation models under the supervision of Dr Edoardo Ponti.


The project is fully funded by the Advanced Research and Invention Agency (ARIA)'s Scaling Compute: AI at 1/1000th the cost (TA 4 Benchmarking) 2M project. As part of this project, we aim to create a suite of next-generation benchmarks that track the fast-evolving landscape of AI, and measure the complex trade-offs across costs, accuracy, and performance on a range of state-of-the-art hardware. This project holds promise to open new avenues in developing and deploying AI models that are fast, environmentally friendly, and energy efficient.



The PDRA will be part of Edinburgh NLP, which is ranked among the top groups in Europe for AI research according to CSRankings. The PDRA will be supervised by Dr Edoardo Ponti and collaborate with other team members based at Edinburgh Informatics, Imperial, and EPCC, one of the UK leading supercomputing centres.



The PDRA role involves 1) conducting cutting-edge research in efficient LLM architectures, building on our lab's pioneering research on end-to-end tokenization and adaptive memory compression in LLMs; and 2) assisting the project team with benchmarking different use cases of foundation models (such as parameter-efficient adaptation and inference-time scaling, among others) on a variety of hardware.



This position includes funding for international travel to attend conferences and offers access to our HPC infrastructure. This position is advertised as full-time (35 hours per week). We are also open to considering requests for hybrid working (on a non-contractual basis) that combines a mix of remote and regular on-campus working.

Please include the following documents in your application:

CV

1-page cover letter

A maximum of 3 scientific papers and a link to a codebase that illustrate the research quality of the candidate and their affinity with the research topic

Your skills and attributes for success:

A PhD or near completion in NLP, ML, MLSys, or related areas of computer science / engineering / mathematics. Track record of research excellence, evidenced by e.g. preprints / publication record. Experience in implementation of foundation models / LLMs, evidenced by e.g. projects on Github. Familiarity with deep learning hardware / accelerators and GPU/CUDA kernels.

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

Contact details for enquiries Edoardo Ponti eponti@ed.ac.uk



Feedback is only provided to interviewed candidates.

As a valued member of our team you can expect:

A competitive salary An exciting, positive, creative, challenging and rewarding place to work. To be part of a diverse and vibrant international community Comprehensive Staff Benefits, such as a generous holiday entitlement, competitive pension schemes, staff discounts, and family-friendly initiatives. Check out the full list on our

staff benefits page

(opens in a new tab) and use our reward calculator to discover the total value of your pay and benefits

Championing equality, diversity and inclusion

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.


Prior to any employment commencing with the University 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).


The University may be able to sponsor the employment of international workers in this role. This will depend on a number of factors specific to the successful applicant.

Key dates to note

The closing date for applications is 23 September 2025.







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