-
of agentic behaviour and publishing high-impact research. Candidates should possess a PhD (or be near completion) in PhD in Computer Science, AI, Security, or a related field. You will have a Strong background
-
to secure future computing systems at lower costs and performance overheads. About you You should possess a PhD/DPhil in Engineering, Computer Science or other related field, (with the possibility
-
publications on AI security. You will also prepare working theories and analyse data from a variety of sources, contribute ideas for new research projects, act as a source of information and advice, and
-
management of sport injuries, with emphasis on safety rather than performance. You will be part of an interdisciplinary team of pioneering researchers, with the primary aim to develop cutting-edge robotics and
-
DPhil students, manage data analysis pipelines, and contribute to publications and grant writing. This post is ideally suited to someone aiming to secure a long-term fellowship and build an independent
-
quality refereed journals and write reports for submission to research sponsors. You must hold a PhD (or be near completion) in a biomedical field of laboratory-based research (ideally immunology and/or
-
fixed-term to the 28th Feb 2027. There has been massive recent interest and efforts into systematic evaluation of the safety of LLM & VLM agents, but these works have focused exclusively on single-agent
-
-established data resources accessed within a secure Trusted Research Environment for large-scale analysis. This role offers excellent opportunities to engage with a broad network of collaborators including
-
research initiative funded by ARIA, titled Aggregating Safety Preferences for AI Systems: A Social Choice Approach. The project operates at the interface of AI safety and computational social choice, and
-
relevant PhD/DPhil in immunology or cell biology (or near completion) together with proven evidence for ability to independently lead and complete impactful research projects that address fundamental