Senior Consultant, AI Safety

Moonshot

Senior freelance consultant red teaming AI systems for Moonshot’s AI Safety portfolio. Developing harm evaluations and interventions across violence, extremism, CSEA, crisis, and teen safety.

Posted 8/22/2026contractRemote • 🇬🇧 United KingdomSeniorWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in trust and safety, particularly in evaluating AI systems against harm categories. Proficient in designing research and evaluation frameworks that translate real-world harm knowledge into actionable criteria.

Highest-signal resume keywords

Trust And Safety ExperienceResearch And Evaluation Framework DesignAdversarial Evaluation Of AI SystemsStrong Written CommunicationModel Safety 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

Red TeamingAdversarial EvaluationCrisis SignallingChild Sexual Exploitation And Abuse (CSEA)Violent Extremism AssessmentIntervention Logic DevelopmentTaxonomy DevelopmentClassifier DevelopmentSafety ToolingUnderstanding Of LLM Architecture

Soft Skills

Sound JudgementResilienceAbility To Work With Sensitive Material

Certifications & Qualifications

Security Clearance

Industry Keywords

Online HarmsViolence PreventionSafeguardingPublic HealthGovernment EngagementPolicy SubmissionsTeen Online SafetyRadicalisation StudiesForensic PsychologyViolence Risk Assessment

About the role

Key responsibilities & impact

Conduct red teaming and adversarial evaluation of AI systems against defined harm categories.
Review model responses against harm and risk criteria and provide expert judgement.
Apply subject matter expertise to harm areas such as grooming and CSEA, radicalisation pathways, crisis signalling, or teen online safety.
Support the design of evaluation frameworks translating real-world harm knowledge into structured, testable criteria.
Contribute to intervention logic connecting at-risk users to appropriate support.
Draft methodology or findings for technical and government audiences.
Work closely with Moonshot's AI Safety team on the delivery of its AI Safety portfolio.
Deliver work within contractual, legal, data protection, and ethics obligations.
Role excludes client relationship management, team leadership, and business development responsibilities.

Requirements

What you’ll need

Experience in trust and safety, online harms, or a closely related field such as violence prevention, safeguarding, or public health, with the ability to apply that knowledge to AI systems.
Demonstrated experience designing research, evaluation frameworks, or interventions for harm categories such as violent extremism, CSEA, self-harm and crisis, or targeted violence.
Ability to translate real world knowledge of how a harm works into a way of testing whether an AI system handles it safely.
Comfort and demonstrated resilience working with highly sensitive or graphic content, including violence, extremist material, and crisis content, with awareness of wellbeing practices for this kind of work.
Strong written communication, able to produce credible, non promotional material for technical and government audiences.
Sound judgement working with ambiguity and sensitive material.
Availability for a close to full time commitment over approximately 6 weeks.
Willingness to undertake relevant security clearance procedures if required by the engagement.
Desirable: genuine depth in model safety, red teaming, or adversarial evaluation of LLMs or other AI systems.
Desirable: understanding of LLM architecture, safety tooling, or trust and safety policy.
Desirable: child safety evaluation, teen safety product work, or grooming and CSEA detection.
Desirable: intervention or diversion programme design transferable to AI-mediated interventions.
Desirable: government or regulatory engagement, such as briefing officials or supporting policy submissions.
Desirable: academic or applied background in radicalisation studies, forensic psychology, or violence risk assessment.
Desirable: taxonomy or classifier development, including how testing data feeds a classifier.

Benefits

Comp & perks

Flexible working arrangements.
Opportunity to work on diverse, impactful projects.
Competitive consultancy rates.
Remote working options available.