Adversarial AI Red-Team Lead

We are looking for a Red Team Specialist to lead the development of adversarial AI models and agents to identify jailbreaks, prompt injections, and misuse cases. The successful candidate will have prior experience in red teaming, adversarial ML, cybersecurity, or socio-technical probing, and strong language skills in English and Korean.

Requirements

• Native-level fluency in English and Korean
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
• Ability to explain risks clearly to technical and non-technical stakeholders

Benefits

• Flexible hours
• Paid weekly

Originally posted on Himalayas