AI and Cybersecurity Threat Assessor

Red Teaming and AI Assurance Expert

We are seeking highly analytical professionals with experience in Red Teaming, prompt evaluation, and Quality Assurance of AI / LLM systems.

• Conduct rigorous exercises to identify vulnerabilities and risks in AI-generated content, ensuring accuracy, bias, and toxicity mitigation.
• Evaluate and stress-test prompts across multiple domains to uncover potential failure modes, collaborating with data scientists and safety researchers.
• Develop test cases to assess performance, security, and reliability in AI-generated responses.

Requirements :

Key Responsibilities :

Our ideal candidate will work collaboratively with cross-functional teams to ensure the highest quality and integrity of AI / LLM systems. If you have a passion for critical thinking and problem-solving, we encourage you to apply for this exciting opportunity.