The post will conduct world-leading research on Neuro-Symbolic Debates for Safeguarded Generative AI, under the direction of Dr Soteris Demetriou, in collaboration with Prof Francesca Toni, Prof Alessandra Russo and other collaborators in the University of Cambridge and in Japan, within the UKRI NeSyDebates project.
It will focus on contributing to developing effective safeguards against undesirable behaviours in Text-to-Image Diffusion Models (T2Is) towards reliable and responsible human-centred AI systems. NeSyDebates aims to focus on requirements (capturing desiderata for safeguarding against undesirable behaviours) expressed by Policies, Regulations and Laws (PRLs in short). Differently from much of the literature using PRLs, NeSyDebates aims to dynamically accommodate conflict-resolution in requirements as well as interactions with humans in a transparent, explainable manner, empowered by debates guided by PRLs. Concretely, NeSyDebates’ objectives are designed to empower (forms of) safeguarded AI specifically with LLMs and T2Is.
The successful applicant will need to interact and collaborate with other partners in NeSyDebates, an international project across the UK and Japan, with the University of Cambridge as an additional UK partner as well as four Japanese institutions, with expertise in AI and/or law. To achieve the objectives, NeSyDebates will develop and deploy novel forms of neuro-symbolic Computational Logic and Argumentation.
The position offers an exciting opportunity for conducting internationally leading and impactful research in AI. The Research Assistant will be responsible for researching, shaping and delivering solutions based on neuro-symbolic debates in a variety of settings (formats, models and data), and will be expected to submit publications to top-tier conferences and journals in AI and Security.
To apply for this position, you must have a strong computer science background with a focus on AI / Security, and have experience, including a proven publication track-record, in at least two of the following areas, as well as ability and willingness to become familiar with the other: neuro-symbolic machine learning, computational argumentation, explainable AI, diffusion models, computer vision, security.
You should also have:
- A Master’s degree (or equivalent) in computer science or related area.
- Familiarity with standard machine learning libraries/data analysis, specifically as concerns LLMs and T2Is. Familiarity with prior works in AI safety.
- Willingness to travel to Japan and to conferences.
- The opportunity to continue your career at a world-leading institution and be part of our mission to continue science for humanity.
- 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 41 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.
Full-time, Fixed term contract to start in January 2027 for 36 months
In addition to completing the online application, candidates should attach:
- A full CV, with a list of all publications
- A 2-page research statement indicating what you see are interesting research issues relating to the above post and why your expertise is relevant.
Informal enquiries related to the position should be directed to Dr Soteris Demetriou: [email protected]
For queries regarding the application process contact Jamie Perrins: [email protected]
Attached documents are available under links. Clicking a document link will initialize its download.
