You will design adversarial prompts and multi-turn interaction chains to test AI models for vulnerabilities related to cyberattacks and malware generation. Additionally, you will evaluate model-generated technical output for functional correctness and document findings within a structured cybersecurity framework.
Design and execute adversarial prompts to test AI model safety against CBRNE threats while documenting failure points. Collaborate with researchers and policy teams to refine evaluation frameworks and improve model defenses.
Evaluate generated images against prompts for quality, composition, and technical defects while classifying them against strict content policies. You will provide evidence-based rationales for your judgments and identify rubric gaps to help train AI models.
Evaluate user requests and AI model responses involving violence, threats, and dark fiction to ensure safety and policy compliance. Identify policy gaps, refine adversarial prompts, and provide clear rationales for classification decisions.
