A complete application in a minute
Tailored resume and cover letter, ready to send.
Imperial College London is seeking a Research Associate in Private and Trustworthy AI to explore information-theoretic foundations for watermarking, privacy, and machine unlearning. The role is based at South Kensington Campus, London, with hybrid work patterns and a fixed-term contract up to 24 months starting January 2027.
You will work within INFORMED-AI, contributing to theory and practical algorithms for reliable AI systems, collaborating with multiple universities and researchers.
Job number ENG04107 Faculties Faculty of Engineering Departments Department of Electrical and Electronic Engineering Salary or Salary range £50,733 - £59,484 per annum Location/campus South Kensington Campus - Hybrid Contract type work pattern Full time - Fixed term Posting End Date 2 Dec 2026
How can we design a watermark that survives editing or paraphrasing? What does it mean, information-theoretically, for a model to have `forgotten’ a training example? What is the price in utility of preventing a model from leaking its training data?
We are seeking a postdoctoral researcher to tackle questions like these within INFORMED-AI, the UKRI AI Hub on Information Theory for Distributed AI (Imperial, Bristol, Cambridge, Durham). The aim is to bring the tools of information and coding theory (e.g., hypothesis testing, channel coding with adversaries, rate-distortion theory, and operational measures of information leakage) to enable trustworthiness of modern generative models, and to turn the resulting insights into practical algorithms.
Potential research directions include, but are not limited to: watermarking and provenance for LLMs and diffusion models (fundamental detectability-quality-robustness trade-offs, watermarks that provably resist adversarial editing, and connections to information hiding and arbitrarily varying channels); machine unlearning (information-theoretic definitions and certificates of forgetting, and efficient algorithms that achieve them); and privacy-preserving training and inference (privacy-utility trade-offs, membership inference and memorisation viewed as hypothesis testing, and privacy in federated and distributed learning).
These questions are extremely timely and important: regulation such as the EU AI Act is beginning to require that AI-generated content be watermarked, while principled answers are still missing. You will be encouraged to develop your own research agenda within this space.
This full-time, in-person postdoctoral position is based at Imperial College’s South Kensington Campus in London, UK, and is funded for up to 24 months, starting in January 2027 or as soon as possible thereafter.
The Research Associate will be supervised by Prof. Deniz Gunduz within the Electrical and Electronic Engineering Department at Imperial College London.
Key responsibilities include:
Education:
Experience
Knowledge
Skills and Abilities
Please note that job descriptions cannot be exhaustive, and the post-holder may be required to undertake other duties, which are broadly in line with the above key responsibilities.
*Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant.
Attached documents are available under links. Clicking a document link will initialize its download.
Please note that job descriptions are not exhaustive, and you may be asked to take on additional duties that align with the key responsibilities mentioned above.
We reserve the right to close the advert before the stated closing date, should we receive a high volume of applications. Please submit your application as early as possible to avoid disappointment.
If you have any general queries about this vacancy, please contact the hiring manager listed in the ‘Further Information’ section. Alternatively, you can contact the Recruitment Hub at recruitmenthub@imperial.ac.uk, and we will be happy to assist you.
If you experience any technical issues that prevent you from submitting an application, please contact our Technical Support team at support.jobs@imperial.ac.uk , who will be able to help resolve the issue.
Welcome to Imperial, a global top-ten university where scientific imagination leads to world-changing impact.
Join us and be part of something bigger. From global health to climate change, AI to business leadership, here at Imperial we navigate some of the world’s toughest challenges. Whatever your role, your contribution will have a lasting impact.
As a member of our vibrant community of 22,000 students and 8,000 staff, you’ll collaborate with passionate minds across nine London campuses and a global network.
This is your chance to help shape the future. We hope you’ll join us at Imperial College London.
We work towards equality of opportunity, eliminating discrimination, and creating an inclusive working environment for all. We encourage applications from all backgrounds, communities and industries, and are committed to employing a team that has diverse skills, experiences and abilities. You can read more about our commitment on our web pages .
Proud signatory of the Armed Forces Covenant. We welcome applications from the Armed Forces community.
Our values are at the root of everything we do, and everyone in our community is expected to demonstrate respect, collaboration, excellence, integrity, and innovation.