Senior AI Safety Red Teaming Consultant (Remote)

Moonshot; United States; Remoto; USD 148.000 - 295.000; Tempo integral

Resumo da vaga

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

You will translate violence prevention and safeguarding expertise into structured outputs for technical and government audiences, working within an ethical and legal framework.

Qualificações

• Experience in trust and safety or online harms with ability to apply to AI systems.
• Designing research, evaluation frameworks, or interventions for harm categories (e.g., violent extremism, CSEA, crisis).
• Translate real-world harm knowledge into testable AI safety evaluations.
• Comfort working with highly sensitive or graphic content and wellbeing practices.
• Strong written communication for technical/government audiences.

Responsabilidades

• Red teaming and adversarial evaluation of AI systems against defined harm categories.
• Reviewing model responses against harm criteria and providing expert judgement.
• Contribute to evaluation framework design translating harm knowledge into criteria.
• Draft methodology or findings for technical and government audiences.

Conhecimentos

Trust & Safety

Online Harms

Risk Assessment

Written Communication

Ambiguity Management

Descrição da vaga

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

You will translate violence prevention and safeguarding expertise into structured outputs for technical and government audiences, working within an ethical and legal framework.