GenAI Security Researcher (Open Ranks), Vulcan

<h2><strong>About Us</strong></h2> <p>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.<br><br></p> <h2><strong>Our Product</strong></h2> <p><span data-contrast="auto">Vulcan is a cybersecurity solution specifically designed for GenAI, offering two core services: Red Team (vulnerability assessment) and Blue Team (real-time defense). It ensures GenAI compliance, cybersecurity robustness, and operational integrity.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;134245417&quot;:false,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <p><span data-contrast="auto">Since its official launch in 2024, Vulcan has been recognized by the international standard-setting organization OWASP as a certified vendor for LLM &amp; GenAI security testing and assessment. It is one of the few solutions capable of supporting multiple Asian languages (Traditional Chinese, Simplified Chinese, Japanese, Korean, Thai) and Standard Arabic.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;134245417&quot;:false,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <p>&nbsp;</p> <h2><strong>The Role</strong></h2> <p>We are seeking a passionate and highly skilled <strong>GenAI Security Researcher</strong> 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.</p> <h2><strong>What You'll Do</strong></h2> <ul> <li>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.</li> <li>Benchmarking: Develop and maintain AI security evaluation frameworks, datasets, and performance metrics.</li> <li>Collaboration: Partner with product and partnership teams to integrate the findings into our AI security solutions.</li> <li>Dissemination: Publish findings in top-tier conferences and journals, present at industry events, and contribute to open-source initiatives.</li> </ul> <h2><strong>What We're Looking For</strong></h2> <ul> <li>Research skills: Advanced degree (e.g., MSc/PhD) with strong analytical thinking, problem-solving skills, and ability to translate research into practical solutions.</li> <li>Knowledge: Deep understanding of relevant techniques, such as generative AI, security &amp; privacy, computer vision, signal processing, and human-computer interaction.</li> <li>Communication skills: Clearly explain complex concepts in layman's terms.</li> <li>Proficiency in English: Write and read documents, communicate with team members in English.</li> <li>Teamwork: Work closely with our members to deliver value.</li> <li>Agility: Adapt quickly to changing research priorities and emerging AI security threats.</li> <li>Coding skills: Proficiency in Python and experience with experimentation.</li> </ul> <h2><strong>Nice to Have</strong></h2> <ul> <li>Publication record in top-tier journals and conferences in AI, security &amp; privacy, computer vision, signal processing, and human-computer interaction.</li> <li>Experience with white-hat hacking and security tools.</li> <li>Familiarity with industry frameworks, such as OWASP Top 10 LLM, MITRE ATT&amp;CK, and security standards.</li> <li>Proficiency in multiple languages.</li> </ul> <h2><strong>Why Join Us</strong></h2> <ul> <li>Solve high-impact AI security challenges shaping the future of trustworthy AI.</li> <li>Collaborate with world-class researchers and engineers in a mission-driven environment.</li> <li>Competitive compensation, flexible working arrangements, and professional growth opportunities.</li> </ul> <h2><strong>How to Apply</strong></h2> <ul> <li>Submit your English CV containing education and work experience with a publication list (underline your name in the author list).</li> </ul>