AI Safety Expert – Red Team

About the role

We are looking for an AI Safety Expert to join our Red Team and help secure conversational AI models and agents. This remote contract position focuses on identifying jailbreaks, prompt injections, and misuse cases while producing actionable reports for our clients.

Key responsibilities

• Red‑team conversational AI models to uncover jailbreaks, prompt injections, and misuse scenarios.
• Generate high‑quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Follow established taxonomies, benchmarks, and playbooks to ensure consistent testing methodology.
• Document findings reproducibly, creating reports, datasets, and attack cases for customer action.
• Review AI outputs on sensitive topics such as bias and misinformation, with optional involvement in higher‑sensitivity projects.

Required profile

• Native fluency in English and Urdu.
• Prior experience in red‑team work, AI adversarial testing, cybersecurity, or socio‑technical probing.
• Ability to clearly explain risks to both technical and non‑technical stakeholders.

Required skills

What we offer

• Hourly compensation of $20–$22.
• Fully remote work arrangement.
• Short‑term contract with flexible hours.