Content Safety Analyst – Remote (AI Red Teaming)

About the role

We are seeking a Content Safety Analyst to join our AI safety team on a remote contract basis. In this role you will apply an adversarial mindset to test conversational AI models and agents, helping customers identify and mitigate systemic risks.

Key responsibilities

• Red‑team conversational AI models by executing jailbreaks, prompt injections, and bias exploitation.
• Generate high‑quality human data through annotation of failures, classification of vulnerabilities, and flagging of systemic risks.
• Follow structured methodologies, taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document findings reproducibly by producing reports, datasets, and attack cases for customer action.

Required profile

• Prior red‑team or adversarial experience in AI, cybersecurity, or socio‑technical probing.
• Curiosity and an adversarial mindset, capable of pushing systems to breaking points.
• Structured approach using frameworks or benchmarks rather than random hacks.
• Strong communication skills to explain risks to both technical and non‑technical stakeholders.
• Adaptability to work across multiple projects and customers.

Required skills