Misuse Red Team - Research Engineer/Research Scientist

About the role

<div class="content-intro"><h2>About the AI Security Institute</h2> <p>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. We’re in the heart of the UK government with direct lines to No. 10 (the Prime Minister's office), and we work with frontier developers and governments globally.</p> <p>We’re here because governments are critical for advanced AI going well, and UK AISI is uniquely positioned to mobilise them. With our resources, unique agility and international influence, this is the best place to shape both AI development and government action.</p></div><h2><strong><span data-contrast="none"><span data-ccp-parastyle="heading 2"></span></span></strong></h2> <h2><span class="TextRun SCXW212922402 BCX8" lang="EN-GB" data-contrast="none"><span class="NormalTextRun SCXW212922402 BCX8" data-ccp-parastyle="heading 2">The deadline for applying to this role is 30</span></span><span class="TextRun SCXW212922402 BCX8" lang="EN-GB" data-contrast="none"><span class="NormalTextRun Superscript CommentHighlightRest SCXW212922402 BCX8" data-fontsize="12" data-ccp-parastyle="heading 2">th</span></span><span class="TextRun SCXW212922402 BCX8" lang="EN-GB" data-contrast="none"><span class="NormalTextRun CommentHighlightRest SCXW212922402 BCX8" data-ccp-parastyle="heading 2">&nbsp;September 2026</span><span class="NormalTextRun CommentHighlightPipeRest SCXW212922402 BCX8" data-ccp-parastyle="heading 2">, end of day, anywhere on Earth.</span></span><span class="EOP Selected SCXW212922402 BCX8" data-ccp-props="{"134245418":true,"134245529":true,"335557856":16777215,"335559738":0,"335559739":0}">&nbsp;</span></h2> <h2><strong><span data-contrast="none"><span data-ccp-parastyle="heading 2"></span></span></strong></h2> <h2><span data-contrast="none"><span data-ccp-parastyle="heading 2">Team Description </span></span><span data-contrast="none"><span data-ccp-parastyle="heading 2">&nbsp;</span></span><span data-ccp-props="{"134245418":true,"134245529":true,"335559738":240,"335559739":240}">&nbsp;</span></h2> <p><span data-contrast="none">Interventions that secure a system from abuse by bad actors or misaligned AI systems will grow in importance as AI systems become more capable, autonomous, and integrated into society.</span><span data-ccp-props="{"335559738":240,"335559739":240}">&nbsp;</span></p> <p><span class="TextRun SCXW184290838 BCX0" lang="EN-GB" data-contrast="none"><span class="NormalTextRun SCXW184290838 BCX0">The Misuse Red Team is a specialised&nbsp;</span><span class="NormalTextRun SpellingErrorV2Themed SCXW184290838 BCX0">subteam</span><span class="NormalTextRun SCXW184290838 BCX0">&nbsp;within AISI's wider Red Team. W</span><span class="NormalTextRun SCXW184290838 BCX0">e&nbsp;</span><span class="NormalTextRun SCXW184290838 BCX0">red</span><span class="NormalTextRun SCXW184290838 BCX0">-</span><span class="NormalTextRun SCXW184290838 BCX0">team&nbsp;</span><span class="NormalTextRun SCXW184290838 BCX0">frontier AI safeguards</span><span class="NormalTextRun SCXW184290838 BCX0">&nbsp;</span><span class="NormalTextRun SCXW184290838 BCX0">for dangerous capabilities</span><span class="NormalTextRun SCXW184290838 BCX0">,&nbsp;</span><span class="NormalTextRun SCXW184290838 BCX0">research&nbsp;</span><span class="NormalTextRun SCXW184290838 BCX0">novel attack vectors</span><span class="NormalTextRun SCXW184290838 BCX0">, and develop advanced automated attack tooling</span><span class="NormalTextRun SCXW184290838 BCX0">. We share our findings with frontier AI companies</span><span class="NormalTextRun SCXW184290838 BCX0">&nbsp;(including&nbsp;</span></span><a class="Hyperlink SCXW184290838 BCX0" href="https://www.anthropic.com/news/strengthening-our-safeguards-through-collaboration-with-us-caisi-and-uk-aisi?subjects=societal-impacts" target="_blank"><span class="TextRun Underlined SCXW184290838 BCX0" lang="EN-GB" data-contrast="none"><

Skills