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.
We are seeking a passionate and highly skilled GenAI Security Researcher to join our team. You will conduct applied and theoretical research into AI vulnerabilities, attack/defense methods, and security/safety benchmarking. Your work will directly shape our AI safety products, contribute to research communities, and influence industry standards and regulations.
Research: Investigate adversarial attacks, data poisoning, prompt injection, jailbreaks, and other AI system vulnerabilities in multi-modalities (e.g., text, image, video, and audio). Design and evaluate mitigation strategies, including fine-tuning, guardrails, content filtering, and robust model architectures.
Benchmarking: Develop and maintain AI security evaluation frameworks, datasets, and performance metrics.
Collaboration: Partner with product and partnership teams to integrate the findings into our AI security solutions.
Dissemination: Publish findings in top-tier conferences and journals, present at industry events, and contribute to open-source initiatives.
Submit your English CV containing education and work experience with a publication list (underline your name in the author list).
Requirements
Research skills: Advanced degree (e.g., MSc/PhD) with strong analytical thinking, problem-solving skills, and ability to translate research into practical solutions.
Knowledge: Deep understanding of relevant techniques, such as generative AI, security & privacy, computer vision, signal processing, and human-computer interaction.
Communication skills: Clearly explain complex concepts in layman's terms.
Proficiency in English: Write and read documents, communicate with team members in English.
Teamwork: Work closely with our members to deliver value.
Agility: Adapt quickly to changing research priorities and emerging AI security threats.
Coding skills: Proficiency in Python and experience with experimentation.