intervu
AI Security Institute logo

AI Security Institute

About the AI Security Institute The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action.

Yes — 5 open roles are live on intervu right now.

aisi.gov.uk · hiring in United Kingdom · 0% of roles remote

Open roles5 of 5 shown

Explore all 5 open roles at AI Security Institute

Screened for postings that aren't really hiring, plus freshness and verified salary transparency.

View all 5 jobs →

Hiring activity

Last 90 days: 6 roles opened, 4 closed.

3 of 5 open roles were posted in the last 30 days.

0 of the 5 roles tracked here may no longer be live.

Company details

Visa & Immigration
80% Roles Sponsored
Flagged as visa-sponsoring on the career page
Computed from this company's own open roles
Tech stack
PythonAWSKubernetesAzure
From active job listings

AI Security Institute in the News

VentureBeatAug 5, 2026

Claude Mythos 5 made sock puppet accounts to socially engineer developers: here's what enterprises should know

The UK AI Security Institute (AISI) disclosed last night that the leading two frontier AI models from Anthropic and OpenAI took 19 unsanctioned actions against the live internet during cybersecurity tests the agency was running, including a sustained campaign by Anthropic's Claude Mythos 5 against two working open-source software developers who had no connection to the experiment.Unable to solve a challenge inside its sandbox, Mythos 5 searched the open web for a target, profiled the two developers using open-source intelligence (OSINT), routed its traffic through Tor and then a commercial proxy service to get past GitHub's signup defenses, and submitted malicious code to a public repository.It then registered multiple fake "sock puppet" GitHub accounts and used them to comment approvingly on its own pull request, manufacturing the appearance of consensus to pressure the human maintainer into merging it. It opened a GitHub Issue seeded with hidden prompt-injection i

Read article

Metrics derived from observed job postings over 90 days — not fundraising data, employee reviews, or third-party valuations.