AI Red Team Analyst

• Conduct red-teaming exercises to uncover AI security weaknesses and deliver findings that improve system safety.
• Craft adversarial prompts, jailbreak attempts, and edge-case scenarios to challenge AI model guardrails.
• Evaluate AI outputs for safety violations, bias, and policy compliance.
• Document vulnerabilities and unexpected behaviours in structured reports for engineering teams.

This role directly enhances the safety and reliability of AI systems, reducing risks of harmful outputs and ensuring responsible AI deployment.

• Experience with AI safety, red-teaming, or adversarial testing.
• Strong understanding of AI model vulnerabilities and security principles.
• Ability to craft creative adversarial prompts and edge-case scenarios.
• Excellent documentation and communication skills for reporting findings.

Compensation and benefits details not specified in the posting.

Alignerr is an organization focused on AI safety and alignment, working to ensure AI systems are secure and beneficial.