Role Responsibilities
- Red team conversational AI models and agents by conducting jailbreaks, prompt injections, and bias exploitation.
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply structured methodologies by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
- Document findings reproducibly by producing reports, datasets, and attack cases for customer action.
Requirements
- Have prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Demonstrate curiosity and an adversarial mindset, pushing systems to their breaking points.
- Be structured in their approach, utilizing frameworks or benchmarks rather than random hacks.
- Possess solid communication skills to explain risks clearly to both technical and non-technical stakeholders.
- Be adaptable and thrive on moving across various projects and customers.
Application Process
- Apply using the Easy Apply button and submit your application.
- Applications will be reviewed based on the role requirements.
- Eligible candidates will receive a message in their LinkedIn inbox with instructions to continue the application process.
- Follow the instructions in the message to complete the remaining application steps.