£48k - £58k
UK jobs. Bigger possibilities.
166,000+ live jobsResearch Associate in Private and Trustworthy AI: Information-Theoretic Foundations
Hybrid in London·Full-time·Added today (last checked 17 Nov)
84 open roles
Our summary
- Salary
- £50,733 - £59,484 a year
About £3,330 - £3,750 a month after tax.
- Work mode
- Hybrid, London
- Contract
- Full-time
- Closing date
- Apply by Wednesday 2 December




Skills
Pay & benefits
What you'll get
- The opportunity to continue your career at a world-leading institution and be part of our mission to continue science for humanity.
- The opportunity to interact and collaborate with researchers across the INFORMED-AI Hub with regular seminars, training schools, and meetings.
- Joint supervision across Imperial and Bristol, with funded research visits, conference travel budget, and access to GPU computing resources.
- Freedom to develop your own research directions, opportunities to co-supervise PhD students, and support for independent fellowship applications (e.g., RAEng, EPSRC).
- Grow your career: gain access to Imperial's sector-leading dedicated career support for researchers as well as opportunities for promotion and progression.
- Sector-leading salary and remuneration package (including 39 days off a year and generous pension schemes).
- Be part of a diverse, inclusive and collaborative work culture with various staff networks and resources to support your personal and professional wellbeing.
The role
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.
What you'll do
- To shape and lead your own research agenda within the themes above
- To undertake original research of international excellence
- To develop fundamental theory with provable guarantees and turn it into practical algorithms evaluated on state-of-the-art generative models
- To write reports for submission to research sponsors
- To present findings at international conferences and contribute to INFORMED-AI Hub activities
- To publish in leading venues in information theory, machine learning and security (e.g., IEEE Trans. IT, ISIT, NeurIPS, ICML, ICLR, COLT, IEEE S&P, USENIX Security)
- To collaborate with researchers at the University of Bristol and across the Hub, and to help mentor PhD students
Education
- Hold a PhD (or be close to completion*) in electrical engineering, computer science, mathematics, statistics, or a related field.
Experience
- Practical experience within a research environment and / or a track record of publications at leading venues
- Strong expertise in one or more of the following, and a willingness to learn the others:
- Optimisation methods.
- Information and coding theory.
- Privacy (e.g., differential privacy) and statistical learning theory.
- Design, implementation and training of deep neural networks.
- Experience with programming in Python and deep learning frameworks (e.g., PyTorch or JAX)
- Desirable: prior work on watermarking, machine unlearning, differential privacy, membership inference or memorisation; hands-on experience with LLMs or diffusion models.
Knowledge
- Knowledge and research experience in one or more of the following areas: information theory, coding theory, learning theory, privacy, optimisation, and generative models (e.g., LLMs and diffusion models).
- Knowledge of research methods and statistical procedures.
Skills and Abilities
- Ability to conduct a detailed review of recent literature
- Ability to develop and apply new concepts
- Creative approach to problem-solving
- Excellent verbal communication skills and the ability to deal with a wide range of people
- Excellent written communication skills and the ability to write clearly and succinctly for publication
About Imperial College London
In their own words
Additional information
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.
How to apply: please submit a CV with a full publication list, a research statement (max. 2 pages) describing how your expertise relates to the themes above, and up to three representative papers. Visa sponsorship is available for this role.
For any specific queries regarding the post please contact Prof Deniz Gunduz (d.gunduz@imperial.ac.uk)
*Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant.
More jobs like this
or browse London·Engineering·Machine learning & AI·Mid-level·Hybrid
