Research Associate/Fellow in AI Safety and Security

at  University of York

DEPARTMENT

You will join the Centre for Assuring Autonomy (CfAA), part of the Department of Computer Science at the University of York. The CfAA is building on the work of the Assuring Autonomy International Programme (AAIP) which pioneered approaches to assuring autonomous systems and their machine learning (ML) components. The CfAA also contributes to the assurance pillar of the Institute for Safe Autonomy (ISA). You will be based in the Institute for Safe Autonomy building.

SKILLS, EXPERIENCE & QUALIFICATION NEEDED

• Successful applicants will have a first degree in computer science or a cognate discipline, and have completed a PhD on AI/ML, ideally with a focus on safety or security of ML models.
• Experience of carrying out both independent and collaborative research.
• Willingness and ability to work as part of a multidisciplinary team.
• Good communication skills including the ability to write up research for publication.
• In addition, for the Research Fellows the successful applicants will have postdoctoral experience and the ability to lead small-scale research projects.
  Interview date: w/c 16th September
  For informal enquiries: please contact Prof John A McDermid on john.mcdermid@york.ac.uk
  The University strives to be diverse and inclusive – a place where we can ALL be ourselves.
  We particularly encourage applications from people who identify as Black, Asian or from a Minority Ethnic background, who are underrepresented at the University.
  We offer family friendly, flexible working arrangements, with forums and inclusive facilities to support our staff. #EqualityatYork

Up to two posts as either a Research Associate or Research Fellow working on assurance of AI-based autonomous systems, as part of the Centre for Assuring Autonomy (CfAA) at the University of York. The roles will enable you to shape the safe introduction of AI-based autonomous systems, across application domains and would be particularly interesting for those who wish to explore the interplay of safety and security in the context of ML models. The posts will have a strong research focus but will also offer the opportunity to work with industry and regulators in the UK and perhaps internationally. Further, the CfAA is a multi-disciplinary centre, offering you the opportunity to learn from others working in different disciplines.