Senior AI Safety Consultant

Job Summary

To support the delivery of an AI Safety portfolio, the remote Senior Freelance Consultant will engage in hands-on technical work focused on red teaming, adversarial evaluation, and methodological development across various harm categories, including violence and exploitation.

Key responsibilities

• Conduct red teaming and adversarial evaluations of AI systems against defined harm categories
• Design and execute evaluation frameworks, translating real-world harm knowledge into structured, testable criteria
• Draft methodologies and findings suitable for technical and government audiences

Required qualifications

• Experience in trust and safety, online harms, or related fields such as violence prevention or public health
• Demonstrated ability to design research and evaluation frameworks for harm categories like violent extremism or CSEA
• Strong written communication skills for producing credible material for technical and government audiences
• Comfort and resilience in handling sensitive or graphic content
• Availability for a close to full-time commitment over approximately 6 weeks