Freelance AI Red Team Specialist
OtherTextRed Teaming
As a Freelance AI Red Team Specialist, I conducted vulnerability testing and prompt injection tests on publicly available AI language models. My work involved analyzing AI model responses for safety, bias, and information leakage, and participating in AI bug bounty programs for responsible AI development. I provided comprehensive documentation and actionable recommendations to improve AI safety. • Conducted adversarial prompt engineering on AI models.
• Evaluated responses for unsafe or unintended outputs.
• Participated in AI model bug bounty programs.
• Used tools such as Lakera Gandalf and Promptfoo for testing.
As a Freelance AI Red Team Specialist, I conducted vulnerability testing and prompt injection tests on publicly available AI language models. My work involved analyzing AI model responses for safety, bias, and information leakage, and participating in AI bug bounty programs for responsible AI development. I provided comprehensive documentation and actionable recommendations to improve AI safety. • Conducted adversarial prompt engineering on AI models. • Evaluated responses for unsafe or unintended outputs. • Participated in AI model bug bounty programs. • Used tools such as Lakera Gandalf and Promptfoo for testing.
2025 - Present