Content Safety Analyst – Remote (AI Red Team)

About the role

We are looking for a Content Safety Analyst to join our AI safety team on a contract basis. You will work remotely, applying red‑team techniques to conversational AI models and agents, helping customers identify and mitigate systemic risks.

Key responsibilities

• Red‑team conversational AI systems 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 taxonomies, benchmarks, and playbooks to ensure consistent and repeatable testing.
• Document findings in reproducible reports, datasets, and attack cases for customer action.

Required profile

• Prior experience in AI adversarial red‑team work, cybersecurity, or socio‑technical probing.
• Curiosity and an adversarial mindset that pushes systems to their breaking points.
• Methodical approach using frameworks or benchmarks rather than ad‑hoc hacks.
• Strong communication skills to convey risks clearly to both technical and non‑technical stakeholders.
• Adaptability to move across multiple projects and customers.

Required skills

What we offer

• Contract position with a compensation range of $20‑$22 per hour.
• Flexible commitment of 10‑40 hours per week.
• Fully remote work environment.