Research EngineerResearch Scientist Red Team (Alignment)

About the AI Security Institute

The AI Security Institute is the worlds largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action. Were in the heart of the UK government with direct lines to No. 10 (the Prime Ministers office) and we work with frontier developers and governments globally.

Were 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.

Team Description

Risks frommisaligned AI systems will grow in importance as AI systems become more capable autonomous and integrated into these risks andstress-testing mitigations ishencecrucial to ensuringadvanced AI systems are developed and deployed safely and beneficially in the future.

The Alignment Red Team is a specialised sub-team within AISIs wider Red Team focused on detecting and evaluating misalignment in frontier AI systems. We perform novel research to develop techniques for finding misalignment and pre- and post-deployment evaluations of frontier AI systems to understand loss-of-control risks associated with models such as deceptive alignment research sabotage and self-exfiltration attempts. We share our findings with frontier AI companies the UK and allied governments to inform their respective deployments research and policy-making. We also work directly with safety teams at frontier labs sharing our evaluation findings to help improve their model alignment training and monitoring methodology.

As an examplewerecentlyconductedpre-deploymenttesting of misalignment risksexamining Claude models forresearch sabotage found that models would sometimesrefuse to help with benign AI safety research an issue whichAnthropic then evaluated for and fixed in their next model release.

About the Role

What Youll Be Doing

• Researchingmethods to automatically search for misalignment in frontier models including misalignment related to loss-of-control risks such as research sabotage and self-exfiltration.

• Buildingand runningalignment evaluationsrelevant for loss-of-control risksthat current benchmarksdontcapture such as research and decision sabotagepower-seekingbehaviouranddeception.

• Running pre-deployment evaluations to test the alignment of AIsystems andanalysing and reporting results to frontier AI companies and UK and allied governments.

• Contributingto public-facing research publications (like our published alignment evaluation case study) and technical reports that advance the fields understanding of alignment risks.
• Designing and building software and tooling including open-source software for better alignment evaluations improving efficiency realism and usability.

The work could also involve:

• Conducting threat modelling analysis and conceptual thinking to understand crucial model behaviours that could lead to loss of control(e.g. AI research assistants at frontier labs) translating abstract risk concepts into concrete testable hypotheses.

• Coordinating and producing holistic assessments of loss-of-control risk from the deployment of AI systems or analysis of such assessments by frontier AI companies.

• Mentoringandadvisingexternal collaborators and researcherstodo work relevant to theteamsgoals and alignment testing more broadly.

What Were Looking For

Wereseeking Research Engineers and Research Scientists to join our Alignment are open to hires at junior senior staff and principal research scientist/engineerlevels.

Essential Requirements

• Ability to work autonomously on complex research projects involving substantial completed at least one substantial research project in AI safety security or alignment involving substantial engineering experimentdesignand analysis on frontier LLMs.

• Strong software engineering and ML experience writing complex projects involving language models and ML beyond just research code.1years professional experienceprogramming in Python for ML or SWE work.

• Ability and experience writing clean documented research code for machine learning experiments including experience with ML frameworks likePyTorchor evaluation frameworks like least one substantial research or engineering project completed.

• Proven ability in a team environment flexible adaptive to needs and willing to contribute wherever necessary.

• Impact-driven mindset motivated by doing the most important work rather thanwhatssuperficially impressive.

• High velocity and high-quality bar for outputs.

Highly Desirable

Wedontexpect candidates to have all of these theyreadditionalsignals that help usidentifyexceptional fits for specific aspects of the role.

• Makes high-qualitydecisions byidentifyingrisks and testing assumptions. Demonstrates this through strong prioritisation of research projectsusing clearsystematic criteriasuch as potentialimpactfeasibility and the relative novelty of the researcharea.

• Familiaritywith alignment literature current methods for post-training and aligning LLMs loss-of-control risks and threat models and the current state of the field.

• High-quality research papers (first author at topMLvenuessuch asNeurIPS ICLR or ICML) particularly in relevant areas(such as AI safety alignment control adversarialMLor evaluations).

• Professional experience working on alignment or evaluations especially at frontier labs or other frontier thirdparty evaluators.

• Strong open-source software projects particularly related to LLMs.

• Proficient usage of LLM coding tools and agents.

What We Offer

Impact youcouldnthave anywhere else

• Incredibly talented mission-drivenand supportive colleagues.

• Direct influence on how frontier AI is governed and deployed globally.

• Work with the Prime Ministers AI Advisor and leading AI companies.

• Opportunity to shape the first & best-resourced public-interest research team focused on AI security.

Resources & access

• Pre-release access to multiple frontier models and ample compute.

• Extensive operational support so you can focus on research and ship quickly.

• Work with experts across national security policy AIresearchand adjacent sciences.

Growth & autonomy

• Ifyouretalented and drivenyoullown important problems early.

• 5 days offand annual stipends forlearning and development andfunding for conferences and external collaborations.

• Freedom to pursue research bets without product pressure.

• Opportunities to publish and collaborate externally.

Life & family*

• Modern central London office (cafes food court gym)orwhere applicableoptionto work in similar government offices in Birmingham Cardiff Darlington EdinburghSalfordor Bristol.

• Hybrid working flexibility for occasional remote work abroad and stipends for work-from-home equipment.

• At least 25 days annual leave 8 public holidays extra team-widebreaksand 3 days off for volunteering.

• Generous paid parental leave (36 weeks of UK statutory leave shared between parents 3 extra paid weeks option foradditionalunpaid time).

• On top of your salary we contribute 28.97% of your base salary to your pension.

• Discounts and benefits for cycling to work donations and retail/gyms.

*These benefits apply to direct employees. Benefits may differ for individuals joining through other employment arrangements such as secondments.

Salary

Annual salary is benchmarked to role scope and relevant experience. Most offers land between 65000 and 145000 made up of a base salary plus a technical allowance (take-home salary base technical allowance). Anadditional28.97% employer pension contribution is paid on the base salary.

This role sits outside of theDDaT pay frameworkgiven the scope of this role requires in depth technicalexpertisein frontier AI safetyrobustnessand advanced AI architectures.

The full range of salaries are available below:

• Level 3:(Base35720 Technical Allowance)

• Level 4:(Base42495 Technical Allowance)

• Level 5:(Base55805 Technical Allowance)

• Level 6:(Base68770 Technical Allowance)

• Level 7:145000(Base68770 Technical Allowance76230)

Selection process

The interview process may vary candidate tocandidatehowever you should expect a typical process to include some technicalproficiencytests discussions with a cross-section of our team at AISI (including non-technical staff) conversations with your team lead. The process will culminate in a conversation with members of the senior leadership team here at AISI.

Candidates should expect to go throughsome orallofthe following stages once an application has beensubmitted:

• Initial assessment

• Initial screening call

• Research interview

• Technical assessment

• Behavioural interview

• Final interview with members of the senior leadership team

Additional Information