AI Safety Experts — English & Malay

• Red team conversational AI models and agents, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to ensure testing consistency.
• Document findings reproducibly by producing reports, datasets, and attack cases for customer action.

• Prior red teaming experience, including AI adversarial work, cybersecurity, or socio-technical probing.
• A curious and adversarial mindset, instinctively pushing systems to their breaking points.
• A structured approach, utilizing frameworks or benchmarks for testing.
• Strong communication skills to explain risks clearly to both technical and non-technical stakeholders.
• Adaptability to thrive when moving across different projects and customers.

• Specialty in Adversarial ML, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.
• Specialty in Cybersecurity, including penetration testing, exploit development, or reverse engineering.
• Specialty in Socio-technical risk, including harassment/disinformation probing, abuse analysis, or conversational AI testing.
• Specialty in Creative probing, involving psychology, acting, or writing for unconventional adversarial thinking.

Project and contracting process: Mercor. Applications continue on the provider's website.