The AI Security Institute is the largest team in the government dedicated to understanding AI capabilities and risks in the world.
Our mission is to equip governments with an empirical understanding of the safety of advanced AI systems. We conduct research to understand the capabilities and impacts of advanced AI and develop and test risk mitigations.
We focus on risks with security implications, including the potential of AI to assist with the development of chemical and biological weapons, how it can be used to carry out cyber-attacks, enable crimes such as fraud, and the possibility of loss of control.
The risks from AI are not sci-fi; they are urgent. By combining the agility of a tech start-up with the expertise and mission-driven focus of government, we’re building a unique and innovative organisation to prevent AI’s harms from impeding its potential.
Research Scientist - Chem Bio | AI Security Institute
London, UK
About the AI Security Institute
The AI Security Institute (AISI), launched at the 2023 Bletchley Park AI Safety Summit, is the world's first state-backed organisation dedicated to advancing AI security for the public interest.
Our mission is to assess and mitigate risks from frontier AI systems, including cyber attacks on critical infrastructure, AI-enhanced chemical and biological threats, large-scale societal disruptions, and potential loss of control over increasingly powerful AI.
In just one year, we've assembled one of the largest and most respected research teams, featuring renowned scientists and senior researchers from leading AI labs such as Anthropic, DeepMind, and OpenAI. At AISI, we're building the premier institution for impacting both technical AI safety and AI governance. We conduct cutting-edge research, develop novel evaluation tools, and provide crucial insights to governments, companies, and international partners.
By joining us, you'll collaborate with the brightest minds in the field, directly shape global AI policies, and tackle complex challenges at the forefront of technology and ethics. Whether you're a researcher, engineer, or policy expert, at AISI, you're not just advancing your career – you're positioned to have a significant impact in the age of artificial intelligence.
ABOUT AISI’s CHEM-BIO WORKSTREAM
You will be part of the Chem-Bio (CB) Team in AISI’s Research Unit, a multidisciplinary team comprised of several technical workstreams and a strategy and delivery function (which serves as an impact multiplier for our technical outputs).
The CB team’s technical work plan is overseen by the CB Workstream Lead, who will also serve as the line manager for this role.
Our team’s mission is to advance the security science of advanced AI models, including LLMs and more specialised AI models within biology and chemistry, and to equip policymakers with an empirical understanding of security-relevant AI capabilities, specifically at the intersection of AI with biology and chemistry.
We work closely across AISI, HMG, and with external experts to make sure our research has real-world impacts on AI safety and chemical and biological security through policy recommendations.
You will lead technical work on thresholds, ecosystem engagement, and conceptual research on mitigations. This may involve defining what AI capabilities would indicate increased risks, leading to research to understand how the academic/industry ecosystem uses different AI tools, or considering what content would be appropriate for an LLM to refuse.
Given the sensitivity of our work, we will need someone who either holds or is able to attain Developed Vetting (DV) and any continued employment will be conditional on earning and maintaining this level of clearance. More details on Security Clearances can be found on the UK Government website.
ROLE SUMMARY
As a Research Scientist, your key duties will span three pillars: Thresholds, Ecosystem Engagement and Mitigations.
Mitigations
- Leading the critical evaluation of frontier AI developers’ capability and safeguard assessments and policies
- Drive forward high-impact collaborations between AISI’s Chem-Bio team and AISI’s Safeguards teams with a focus on risk mitigation projects (i.e. developing an evaluation to assess biological and chemical classifiers robustness)
- Serve as a biosecurity resource for developers
Thresholds
- Lead the team’s work on defining key risk/capabilities thresholds and strategies for operationalising these
- Ensure compatibility across risk models and AISI’s internal evaluation suite
Ecosystem
- Oversee external collaborations between AISI’s Chem-Bio team and frontier AI developers
- Maintain awareness of cutting-edge research across academia and industry on frontier AI models, science agents and risk mitigation strategies
- Lead the design and development of collaborations to understand the use of AI across the research and scientific communities and the implications of this use for AISI’s future work
PERSON SPECIFICATION
We strongly encourage you to apply even if you feel you only meet some of the criteria listed here.
Essential Criteria
- Background in biological/chemical science or machine learning
- A strong track record of research or professional experience in biosecurity or AI governance
- Knowledge of prominent approaches for mitigating risks from frontier AI systems.
- Strong strategic sense for driving real-world impact.
- Experience shaping and driving research agendas or policy work
Desirable Criteria
- Strong knowledge of chemical/biological models and their unique safety considerations.
- Background or strong working level knowledge on microbiology or virology.
- Experience with forecasting or survey research.
- A strong network in the AI-chem/bio and biosecurity communities.
- Excellent written and verbal communication skills.
- Experience in engaging with a diverse set of technical and non-technical stakeholders.
If you have questions about the role, AISI’s Chem-Bio Workstream Lead (Sophie Rose; Sophie.Rose@dsit.gov.uk) is available to discuss it further.
Clearance Criteria
Whilst AISI often encourages applications from individuals of any nationality, due to the unique nature of this role and the elevated security clearances that would be required once in post, we can only accept individuals capable of meeting DV criteria, which is largely restricted to UK nationals.
Therefore, this statement supersedes our general nationality rules policy as described in the footnote of this post. For further vetting clarification, please visit the GOV.UK site listed below: National security vetting: clearance levels - GOV.UK
Salary & Benefits
We are hiring individuals at all ranges of seniority and experience within this research unit, and this advert allows you to apply for any of the roles within this range. Your dedicated talent partner will work with you as you move through our assessment process to explain our internal benchmarking process. The full range of salaries are available below, salaries comprise of a base salary, technical allowance plus additional benefits as detailed on this page.
- Level 3 - Total Package £65,000 - £75,000 inclusive of a base salary £35,720 plus additional technical talent allowance of between £29,280 - £39,280
- Level 4 - Total Package £85,000 - £95,000 inclusive of a base salary £42,495 plus additional technical talent allowance of between £42,505 - £52,505
- Level 5 - Total Package £105,000 - £115,000 inclusive of a base salary £55,805 plus additional technical talent allowance of between £49,195 - £59,195
- Level 6 - Total Package £125,000 - £135,000 inclusive of a base salary £68,770 plus additional technical talent allowance of between £56,230 - £66,230
- Level 7 - Total Package £145,000 inclusive of a base salary £68,770 plus additional technical talent allowance of £76,230
This role sits outside of the DDaT pay framework, given the scope of this role requires in-depth technical expertise in frontier AI safety, robustness and advanced AI architectures.
There is a range of pension options available, which can be found through the Civil Service website.
