Freelance AI Red Team Engineer

Mindrift is seeking AI Red Team Engineers to evaluate and improve the safety and capabilities of Generative AI models. This is a fully remote, part-time opportunity involving tasks like vulnerability testing, automation scripting, and security research. The role offers a chance to contribute to ethically shaping the future of AI and benefit from the project's focus on AI safety.

Requirements

• Bachelor's or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, Digital Forensics or related field
• Advanced English proficiency (C1 or higher)
• Proficiency in Python, Bash, or PowerShell
• Experience with containerization and CI/CD security tools (Docker)
• Hands-on experience with penetration testing across various environments
• Knowledge of vulnerabilities in current AI models (prompt injections, LLMs)
• Familiarity with AI red-teaming frameworks (garak or PyRIT)
• Experience in AI/ML security, evaluation, and red teaming, particularly with LLMs
• Proficient in offensive exploitation and exploit development
• Skilled in reverse engineering and reverse engineering with Ghidra or equivalents
• Expertise in network and application security, including web application security
• Knowledge of operating system security concepts (Linux, Windows)

Benefits

• Remote work opportunity
• Competitive rates
• Professional development
• Contribution to AI safety