Senior Research Scientist – AI Safety Evaluations

Faculty

. Lead development of novel safety evaluations in high-impact domains such as CBRN and Cyber .

Posted 10/8/2026full-timeLondon • United KingdomSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in AI safety evaluation methodologies, including experimental design, statistical analysis, and robust research practices. Proven ability to lead research projects from concept to publication while engaging with diverse stakeholders in high-impact domains such as CBRN and Cybersecurity.

Highest-signal resume keywords

AI Safety Evaluation MethodologiesExperimental DesignStatistical AnalysisPython ProficiencyRed-Teaming Expertise

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

AI EvaluationsBayesian MethodsGenerative AI ArchitecturesSafety Mitigation TechniquesThreat ModellingRisk ModellingAdversarial TestingJailbreakingIndirect Prompt InjectionConstruct Validity

Industry Keywords

CBRNCybersecurityHigh-Impact AI ResearchScientific PublicationsTechnical ReportsResearch and DevelopmentClient Delivery ProjectsGlobal Research CommunityFrontier LabsGovernment Stakeholders

Tech Stack

Tools & technologies

Cyber SecurityPython

About the role

Key responsibilities & impact

Lead development of novel safety evaluations in high-impact domains such as CBRN and Cyber
Execute original technical research in AI safety evaluation methods from concept to publication
Shape the R&D agenda by identifying strategic opportunities to advance safety evaluation methodology
Contribute technical expertise to client delivery projects, evaluation work, and red-teaming for frontier labs
Represent Faculty’s scientific leadership through engagement with the global research community, frontier labs, and government stakeholders
Produce scientific outputs including publications, tooling, technical reports, and evaluations
Collaborate with Faculty’s wider AI safety team and delivery teams

Requirements

What you’ll need

Track record of owning research end-to-end, from identifying novel problems to publication
Hands-on experience designing and building AI evaluations or benchmarks
Ability to reason about construct validity and mitigate confounds
Expertise in red-teaming, adversarial testing, jailbreaking, indirect prompt injection, and assessing model safeguard robustness
Strong foundational skills in experimental design, statistical analysis, and uncertainty quantification, including Bayesian methods
Deep knowledge of language models, generative AI architectures, training methodologies, and safety mitigation techniques
Solid Python proficiency
Engineering discipline for robust, reproducible research
Experience in threat and risk modelling (nice to have)
Background or knowledge in CBRN or Cybersecurity (nice to have)
History of high-impact AI research evidenced by top-tier publications or equivalent practical achievements (nice to have)
Visa sponsorship requirements for working in the UK are assessed during application

Benefits

Comp & perks

Openness to conversations about part-time hours
Diversity and inclusion-focused recruitment ethos
Opportunity to use AI for research and interview preparation
Human review of every application
AI interview note-taker opt-out available