- Red team conversational AI models and agents to identify vulnerabilities.
- Generate high-quality human data by annotating failures and classifying vulnerabilities.
- Apply structured methodologies to ensure consistent testing.
- Document findings reproducibly to produce actionable reports and datasets.
Requirements
- Have robust relevant experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Demonstrate curiosity and adversarial thinking to push systems to breaking points.
- Utilize frameworks or benchmarks for structured testing.
- Communicate risks clearly to both technical and non-technical stakeholders.
- Adaptability to move across various projects and customer needs.
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 or email inbox with instructions to continue the application process.
- Follow the instructions in the message to complete the remaining application steps.