Senior/Staff AI Security & Red-Team Engineer

Promptfoo is looking for a Senior or Staff AI Security & Red-Team Engineer to strengthen our security capabilities. You will design and implement innovative ways to test and secure LLM applications, drawing from Promptfoo’s expertise in vulnerability scanning and red teaming. This role requires deep technical knowledge of AI systems and security best practices.

Key Responsibilities:

• Develop and maintain Promptfoo’s red-teaming capabilities
• Design automated security tests for LLM applications
• Collaborate with researchers to identify and address vulnerabilities
• Build tools for detecting prompt injections, data leaks, and other security issues
• Contribute to our foundation model reports and security database
• Stay informed about the latest AI security research and techniques
• Mentor junior engineers in security practices

Required Skills:

• 7+ years of experience in AI/ML security or red teaming
• Strong programming skills in Python or similar languages
• Understanding of LLM vulnerabilities and attack vectors
• Experience with automated testing frameworks
• Familiarity with machine learning concepts
• Excellent analytical and problem-solving abilities

As a key member of our security team, you will help build the tools that protect developers from deploying insecure AI applications. This role offers the chance to work at the intersection of cutting-edge AI and cybersecurity.