Misuse Red Team - Research Engineer/Research Scientist - Job Hub - Epelcon Global: Long Life and Prosperity for All.

Job Description

<div class="content-intro"><h2>About the AI Security Institute</h2> 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. 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.</div><h2></h2> <h2>The deadline for applying to this role is 30th September 2026, end of day, anywhere on Earth. </h2> <h2></h2> <h2>Team Description   </h2> 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.  The Misuse Red Team is a specialised subteam within AISI's wider Red Team. We red-team frontier AI safeguards for dangerous capabilities, research novel attack vectors, and develop advanced automated attack tooling. We share our findings with frontier AI companies (including <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">Anthropic</a>, <a class="Hyperlink SCXW184290838 BCX0" href="https://openai.com/index/us-caisi-uk-aisi-ai-update/" target="_blank">OpenAI</a>, <a class="Hyperlink SCXW184290838 BCX0" href="https://deepmind.google/blog/deepening-our-partnership-with-the-uk-ai-security-institute/" target="_blank">DeepMind</a>), key UK officials, and other governments to inform their respective deployment, research, and policy decision-making.  We have published on several topics, including novel automated attack algorithms (<a href="https://arxiv.org/abs/2602.15001">Boundary Point Jailbreaking</a>), <a href="https://arxiv.org/abs/2510.07192">poisoning attacks,</a> <a href="https://www.aisi.gov.uk/work/making-safeguard-evaluations-actionable">safeguards safety cases,</a> <a href="https://arxiv.org/abs/2502.14828">defending finetuning APIs,</a> <a href="https://www.nist.gov/news-events/news/2025/01/technical-blog-strengthening-ai-agent-hijacking-evaluations">third-party attacks on agents,</a> <a href="https://arxiv.org/abs/2410.09024">agent misuse</a>, and <a href="https://www.aisi.gov.uk/research">pre-training data filtering</a>. Some example impact cases have been advancing the benchmarking of agent misuse, identifying novel vulnerabilities and collaborating with frontier labs to mitigate them, and producing insights into the feasibility and effectiveness of attacks and defences in data poisoning and fine-tuning APIs.    <h2>Role Description   </h2> We’re looking for research scientists and research engineers for our misuse sub-team with expertise developing and analysing attacks and protections for systems based on large language models or who have broader experience with frontier LLM research and development. An ideal candidate would have a strong track record of performing and publishing novel and impactful research in these or other areas of LLM research. We’re looking for:  <ul> <li>Research Scientists, who typically lead technical direction – picking the questions, designing the experiments, and owning the conclusions (typically evidenced by a strong publication record). </li> <li>Research Engineers, who typically lead execution – building the systems and code that make those experiments possible at scale, and owning reliability, speed, and reproducibility. </li> </ul> In practice, we can support staff’s work spanning or alternating between research and engineering. If you have a preference, please specify this in your application.  The team is currently led by <a href="https://www.aisi.gov.uk/people/eric-winsor">Eric Winsor</a> and <a href="https://x.com/alxndrdavies?lang=en">Xander Davies</a>. You’ll work with incredible technical staff across AISI, including alumni from Anthropic, OpenAI, DeepMind, and top universities. You may also collaborate with external teams from Anthropic, OpenAI, and Gray Swan.     We are open to hires at junior, senior, staff and principal research scientist levels.     <h3>Representative projects you might work on   </h3> <ul> <li data-leveltext="" data-font="Symbol" data-listid="2" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="1" data-aria-level="1">Designing, building, running and evaluating methods to automatically attack and evaluate safeguards, such as LLM-automated attacking and direct optimisation approaches.   </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="2" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="2" data-aria-level="1">Building a benchmark for asynchronous monitoring for signs of misuse and jailbreak development across multiple model interactions.   </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="2" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="3" data-aria-level="1">Investigating novel attacks and defences for data poisoning LLMs with backdoors or other attacker goals.   </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="2" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="4" data-aria-level="1">Performing adversarial testing of frontier AI system safeguards and producing reports that are impactful and action-guiding for safeguard developers.   </li> </ul> <h2>What we’re looking for   </h2> The experiences listed below should be interpreted a

Skills Required

Red Team

Job Details

Salary: Negotiable

Type: Full time

Mode: On site

Views: 1

Applications: 0

Members Only