Adversarial AI Testing & Red Team Specialist

Freelancing; Malaysia; Remote; MYR 83,000 - 165,000; Full time

Job summary

A technology consulting firm based in Malaysia is seeking a human data expert to red team AI models, probing them against adversarial inputs. The successful candidate will generate high-quality human data, classify vulnerabilities, and document findings to enhance AI safety. A prior background in adversarial work, strong communication skills, and adaptability are essential for this role, as you'll navigate various sensitive projects with clear guidelines to ensure safety and effectiveness.

Qualifications

• Experience in adversarial work related to AI or cybersecurity.
• Ability to explain risks and methodologies to diverse audiences.
• Experience with socio-technical risk analysis in AI contexts.

Responsibilities

• Red team conversational AI models and agents using various techniques.
• Generate high-quality human data by annotating failures and vulnerabilities.
• Follow structured methodologies to ensure consistency in testing.
• Document processes and findings in clear reports and datasets.

Skills

Prior red teaming experience

Curiosity and adversarial mindset

Structured approach using benchmarks

Effective communication skills

Adaptability

Job description

A technology consulting firm based in Malaysia is seeking a human data expert to red team AI models, probing them against adversarial inputs. The successful candidate will generate high-quality human data, classify vulnerabilities, and document findings to enhance AI safety. A prior background in adversarial work, strong communication skills, and adaptability are essential for this role, as you'll navigate various sensitive projects with clear guidelines to ensure safety and effectiveness.