Mindrift is seeking AI Red Team Engineers to collaborate on innovative projects utilizing the power of collective intelligence to shape the future of AI. The role focuses on vulnerability assessment, security research, and advising on cybersecurity best practices within the context of Generative AI models. Candidates need to be proficient in automation, penetration testing, and knowledge of LLMs and AI red-teaming frameworks.
Requirements
- Bachelor’s or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, Digital Forensics, or related field
- Advanced English proficiency (C1 or above)
- Proficiency in Python, Bash, or PowerShell
- Experienced with containerization and CI/CD security tools (Docker)
- Hands-on experience with penetration testing across various environments (web, API, network, infrastructure)
- Knowledge of AI models vulnerabilities, including prompt injections
- Experience with AI/ML security frameworks (Gakar or PyRIT)
- Experience with offensive exploitation and reverse engineering
- Expertise in network and application security
- Knowledge of operating system security concepts
- Familiarity with secure coding practices for full-stack development
Benefits
- Remote work
- Competitive rates
- Opportunity to work on advanced AI projects