Senior AI Safety Red Team Consultant - Remote

Moonshot; Ireland; À distance; EUR 165 000 - 248 000; Plein temps

Avantages offerts par ce poste

Flexible working arrangements

Diverse, impactful projects

Competitive consultancy rates

Remote working options available

Résumé du poste

Moonshot is seeking a Senior Freelance Consultant to support the delivery of our AI Safety portfolio. This hands-on engagement focuses on red teaming, adversarial evaluation, and methodological development across harm categories including online safety, crisis signals, and teen safety.

You will work with Moonshot's AI Safety team to design evaluation frameworks, scoring criteria, and test scenarios, translating domain expertise into outputs for technical and government audiences.

Qualifications

• Experience in trust and safety or related field applicable to AI.
• Ability to design research, evaluation frameworks, or interventions for harm categories.
• Translate real-world harm knowledge into testing of AI systems.
• Comfort with sensitive or graphic content and wellbeing practices.
• Strong written communication for technical and government audiences.
• Sound judgement when working with ambiguity and sensitive material.
• Availability for close to full-time commitment over ~6 weeks.
• Willingness to undertake security clearance procedures if required.

Responsabilités

• Red teaming and adversarial evaluation of AI systems against defined harm categories.
• Reviewing model responses against harm and risk criteria and providing expert judgement.
• Bringing subject matter expertise to harm areas such as grooming and CSEA, radicalisation pathways, crisis signalling, teen online safety.
• Supporting the design of evaluation frameworks translating harm knowledge into structured, testable criteria.
• Contributing to intervention logic that connects at risk users to appropriate support.
• Drafting methodology or findings suitable for technical and government audiences.

Connaissances

Trust and safety

Evaluation design

AI risk testing

Sensitive content

Technical writing

Ambiguity tolerance

6-week availability

Security clearance

Description du poste

Moonshot is seeking a Senior Freelance Consultant to support the delivery of our AI Safety portfolio. This hands-on engagement focuses on red teaming, adversarial evaluation, and methodological development across harm categories including online safety, crisis signals, and teen safety.

You will work with Moonshot's AI Safety team to design evaluation frameworks, scoring criteria, and test scenarios, translating domain expertise into outputs for technical and government audiences.