Role OverviewAI Safety Expert - Red Team will work independently and asynchronously to identify jailbreaks, prompt injections, and misuse cases in conversational AI models and agents. The role involves annotating failures, classifying vulnerabilities, and flagging systemic risks. The expert will apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing and document reproducibly by producing reports, datasets, and attack cases.
What You Will Do
The main day-to-day responsibilities include red teaming conversational AI models and agents, generating high-quality human data, applying structure to maintain consistent testing, and documenting reproducibly.
Why It Might Be a Fit
The ideal candidate will have 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, and experience with Adversarial ML, Cybersecurity, and Socio-technical risk.
Requirements
- Fluent in English and Bengali
- 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
]]>