Role OverviewThe AI Adversarial Specialist will work independently and asynchronously to uncover vulnerabilities in conversational AI models and agents, and improve AI model performance. The role requires fluent language skills in English and Vietnamese, and prior experience in AI adversarial work, cybersecurity, or socio-technical probing. The Specialist will work with the team to identify jailbreaks, prompt injections, and misuse cases, and document reproducibly to produce reports, datasets, and attack cases that customers can act on.
What You Will Do
The main day-to-day responsibilities of the AI Adversarial Specialist will include red teaming conversational AI models and agents, generating high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks, and applying structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
Why It Might Be a Fit
The ideal candidate will have experience with Adversarial ML, Cybersecurity, or socio-technical risk analysis, and skills in creative probing such as psychology, acting, or writing. The Specialist will need to explain risks clearly to technical and non-technical stakeholders, and work independently and asynchronously to uncover vulnerabilities and improve AI model performance.
Requirements
- Fluent Language Skills in English & Vietnamese
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Ability to explain risks clearly to technical and non-technical stakeholders
]]>