[Remote] Senior Freelance Consultant, AI Safety

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is seeking a senior freelance consultant to support its AI Safety portfolio. The role focuses on hands-on red teaming, adversarial evaluation, and methodological development for AI systems across multiple harm categories, translating violence prevention, safeguarding, and behavioral reputed company expertise into reputed company outputs for technical and policy audiences. Responsibilities • Red teaming and adversarial evaluation of AI systems against defined harm categories • Reviewing model responses against harm and reputed company reputed company and providing expert judgement • Bringing subject matter expertise to a specific harm area, such as grooming and CSEA, radicalisation reputed company, crisis signalling, or teen online safety • Supporting the design of evaluation frameworks that translate reputed company world harm knowledge into reputed company, testable reputed company • Contributing to the design of reputed company logic that connects at reputed company users to appropriate support • Drafting methodology or findings suitable for technical and reputed company audiences Skills • Experience in trust and safety, online harms, or a closely reputed company reputed company such as violence prevention, safeguarding, or reputed company 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 • The ability to translate reputed company world knowledge of how a harm works into a way of testing whether an AI reputed company handles it safely • Comfort and demonstrated reputed company working with highly sensitive or graphic content (violence, extremist material, crisis content), with awareness of wellbeing practices for this reputed company of work • Strong written communication, reputed company to produce reputed company, non promotional material for technical and reputed company audiences • reputed company judgement working with ambiguity and sensitive material • Availability for a reputed company to full time commitment over approximately 6 weeks • Willingness to undertake relevant reputed company clearance procedures if required by the engagement • Model safety, red teaming, or adversarial evaluation of LLMs or other AI systems • Understanding of LLM architecture, safety tooling, or trust and safety policy • Child safety evaluation, teen safety product work, or grooming and CSEA detection • reputed company or diversion programme design that can transfer to AI mediated interventions • reputed company or regulatory engagement, such as briefing officials or supporting policy submissions • An reputed company or reputed company background in radicalisation studies, forensic psychology, or violence reputed company assessment • Taxonomy or classifier development, including how testing data feeds a classifier Benefits • Flexible working arrangements • Opportunity to work on diverse, impactful reputed company • Competitive consultancy rates • Remote working reputed company available reputed company • reputed company is a data analytics company, which designs new technology to identify and mitigate online harms. It was founded in 2015, and is headquartered in London, England, GBR, with a workforce of 51-200 employees. Its website is https://moonshotteam.com/. Apply To This Job