GenAI Security Researcher

Responsibilities

• Investigate adversarial attacks, data poisoning, prompt injection, and jailbreaks across multi-modalities including text, image, video, and audio
• Design and evaluate mitigation strategies such as fine-tuning, guardrails, and robust model architectures
• Develop and maintain AI security evaluation frameworks, datasets, and performance metrics
• Partner with product teams to integrate research findings into AI security solutions
• Publish research findings in top-tier conferences and journals and contribute to open-source initiatives

Requirements

• Advanced degree (MSc or PhD) in a relevant field
• Deep understanding of generative AI, security, and privacy
• Proficiency in Python and experience with experimental research
• Strong analytical thinking and problem-solving skills
• Proficiency in English for technical documentation and team communication

Preferred Qualifications

• Publication record in top-tier AI, security, or computer vision conferences
• Experience with white-hat hacking and security tools
• Familiarity with industry frameworks like OWASP Top 10 LLM or MITRE ATT&CK
• Proficiency in multiple languages

Benefits

• Solve high-impact AI security challenges shaping the future of trustworthy AI
• Collaborate with world-class researchers and engineers in a mission-driven environment
• Competitive compensation and flexible working arrangements

About the Company

AIFT is at the forefront of AI safety and security. We develop cutting-edge solutions, including Vulcan Attack for automated vulnerability assessment and Vulcan Protect for real-time monitoring, to ensure AI systems are robust, trustworthy, and aligned with societal needs.