Role OverviewThe AI Safety Expert - Red Team will be responsible for conversational AI models and agents, focusing on jailbreaks, prompt injections, and misuse cases. They will generate high-quality human data, annotate failures, classify vulnerabilities, and flag systemic risks. The role requires strong communication skills to explain risks to technical and non-technical stakeholders.
What You Will Do
The main day-to-day responsibilities will include conversational AI testing, generating human data, annotating failures, classifying vulnerabilities, and flagging systemic risks. The role also involves documenting reproducibly and producing reports, datasets, and attack cases that customers can act on.
Why It Might Be a Fit
To be a fit for this role, you should have prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing. You should also have strong communication skills to explain risks to technical and non-technical stakeholders. Experience in Adversarial ML, cybersecurity skills, and socio-technical risk expertise are preferred.
Requirements
- Native fluency in English and Portuguese (global, excluding Brazilian Portuguese)
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Strong communication skills to explain risks to technical and non-technical stakeholders
]]>