GenAI Security Researcher - Remote

Overview

AIFT is at the forefront of AI safety and security, developing cutting-edge solutions, Vulcan Attack (automated vulnerability assessment/red teaming) and Vulcan Protect (real-time monitoring), to ensure AI systems are robust, trustworthy, and aligned with societal needs.

In Short

• Conduct applied and theoretical research into AI vulnerabilities.
• Investigate adversarial attacks, data poisoning, and other vulnerabilities.
• Design and evaluate mitigation strategies for AI security.
• Develop and maintain AI security evaluation frameworks.
• Collaborate with product teams to integrate findings into solutions.
• Publish research findings in top-tier conferences and journals.
• Communicate complex concepts clearly to various audiences.
• Work in a dynamic environment adapting to emerging threats.
• Proficient in Python for coding and experimentation.
• Engage in teamwork to deliver value effectively.

Requirements

• Advanced degree (e.g., MSc/PhD) in relevant field.
• Deep understanding of generative AI and security techniques.
• Strong analytical thinking and problem-solving skills.
• Proficiency in English for communication and documentation.
• Able to adapt quickly to changing research priorities.
• Experience in white-hat hacking and security tools is a plus.
• Publication record in AI-related fields is advantageous.
• Familiarity with industry frameworks like OWASP and MITRE.
• Ability to work closely with team members.
• Proficiency in multiple languages is a nice to have.

Benefits

• Solve high-impact AI security challenges.
• Collaborate with world-class researchers and engineers.
• Competitive compensation and flexible working arrangements.
• Opportunities for professional growth.