ARIA: Safeguarded AI: Technical Areas 1.2 + 1.3

Backed by £14.2m, ARIA (the UK’s Advanced Research and Innovation Agency) are looking to fund teams of software developers to build the scaffolding needed for the success of the Safeguarded AI programme.

For TA 1.2, we are looking for Creators to develop the computational implementation of the theoretical frameworks being developed as part of TA 1.1 (the ‘Theory’). This implementation will involve version controlling, type checking, proof checking, security-by-design, flexible paradigms for interactions between humans and AI assistants, among others.

For TA 1.3, Creators will work on the ‘Human-Computer Interfaces’ that facilitate interaction between diverse human users and the systems being built in TA 1.2 and TA 2 (‘Machine Learning’). Examples of HCI use cases include AI assistants helping to author and review world models and safety specifications, or helping to review guarantees and sample trajectories for spot/sense-checking or more comprehensive red-teaming.

These technical areas are integral to supporting the programme’s wider ambition of demonstrating the viability of a new, alternative pathway for research and development toward safe and transformative AI.

We expect to fund 3-6 teams across TA1.2 & TA1.3, for a total of £14.2m. The projects will last 27 months in the case of TA1.2, and 30 months for TA1.3, with a ‘go/no-go’ decision point after the first 12 months. Applicants can apply to either or both of these TAs at the same time.

Support and resources

Download the complete call for proposals (PDF)

Safeguarded AI TA1.2/TA1.3: Solicitation presentation video

Who can apply?

ARIA welcome solicited applications from across the R&D ecosystem, including individuals, universities, research institutions, small, medium and large companies, charities and public sector research organisations. We are keen to explore structures not typical in academic research, such as supporting early career researchers as project leads or funding large (>80%) proportions of senior academics’ time so that they can focus fully on their ARIA project.

We are primarily looking for applications from software development organisations, especially teams with strong mathematical backgrounds (for work in TA1.2), and/or strong design/HCI/UX capabilities (for work in TA1.3). Ideal applicants would have a compelling track record for delivering innovative and bespoke software solutions, including working with multiple stakeholder groups to elicit requirements, test and iterate on solutions.

We do not anticipate any single applicant having the requisite variety of skillsets for the entirety of these TAs, but we hope to assemble the breadth & depth of the required expertise from a small number of applicants each contributing their own specialties. We also expect that, rather than from the get go having the full capacity required to deliver the proposed projects, some successful applicants will begin to recruit and hire additional staff during the early phase of the project.