GenAI Analyst

• Test Generative AI models by writing adversarial prompts to identify security vulnerabilities.
• Develop prompt strategies across multiple abuse categories to expose model weaknesses.
• Manage projects end-to-end from planning through quality assurance to final delivery.
• Handle multilingual datasets across abuse areas with meticulous precision and attention to detail.

This role directly contributes to making Generative AI safer by identifying and mitigating security vulnerabilities before they can be exploited.

• Experience with adversarial testing or red-teaming of AI systems.
• Strong project management skills.
• Attention to detail and ability to handle multilingual datasets.
• Knowledge of emerging tactics for circumventing safety measures.

Compensation and benefits not specified in the job posting.

Alice is an organization focused on AI safety, working to ensure generative AI models are secure and trustworthy.