Step into a critical role as an AI Safety Red Teamer, where you'll design prompts and evaluate AI models to ensure safety in ambiguous contexts. Tackle challenging scenarios head-on.

In this role, you'll be responsible for identifying vulnerabilities within AI models, leveraging your extensive experience in safety and cybersecurity. With a focus on evaluating their robustness in sensitive domains, you will document findings and collaborate with researchers to enhance AI alignment. Strong analytical skills and effective communication are integral to succeed.

Key Responsibilities:
• Create adversarial prompts for AI stress tests
• Identify policy failures and unsafe behaviors in AI
• Evaluate AI systems across nuanced areas
• Provide detailed reporting on vulnerabilities
• Work with researchers to improve safety protocols

Requirements:
• Bachelor’s degree in relevant fields
• Over 5 years of related professional experience
• Skilled in analytical reasoning and prompt engineering
• Familiarity with evaluating AI systems
• Strong written communication skills

Contribute to advancing AI technology through safety-focused evaluations and creative prompt design.
#J-18808-Ljbffr

📌 Expert AI Safety Red Team Member (Manitoba)
🏢 Great Value Hiring
📍 Manitoba