What We Are Looking For As a PR GenAI Security Researcher, you will design novel attacks on GenAI applications and share your findings with the broader community. Your primary responsibility will be to ideate, prototype, and exploit GenAI applications, RAG pipelines, and multi-agent systems, turning your discoveries into talks, papers, and workshops. We are looking for an experienced security researcher with peer-reviewed publications, experience organizing cybersecurity workshops, a proven track record of jailbreaking commercial models, and a talent for creating engaging content. This role is ideal for someone who can not only uncover vulnerabilities but also educate, inspire, and lead the global security community.
Key Responsibilities
* Proactively discover and responsibly disclose novel vulnerabilities and attack vectors in commercial and open-source GenAI models.
* Create compelling and accessible content (e.g., blog posts, videos, tutorials) that translates complex research into insights for a wider audience.
* Author and publish peer-reviewed papers in top-tier cybersecurity conferences (e.g., Black Hat, DEF CON, RSA, CCC).
* Develop and lead public workshops and technical tutorials to share new security techniques and countermeasures with the community.
About ActiveFence:
ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the world’s largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Requirements: Must-Have
* 4+ years of hands-on cybersecurity research experience, with a focus on offensive security or adversarial machine learning in AI/GenAI contexts.
* Proven ability to identify and exploit vulnerabilities in AI systems, including jailbreaking commercial large language models or executing complex multi-step attacks on AI-driven platforms.
* Strong programming and scripting skills (e.g., Python) to build end-to-end proof-of-concept exploits and automation tools.
* Demonstrated track record as an author with peer-reviewed publications in top-tier cybersecurity conferences (e.g., Black Hat, DEF CON, RSA, CCC). Nice-to-Have
* Experience presenting research at conferences, workshops, or industry events.
* Familiarity with industry-standard AI security frameworks and guidelines, including OWASP’s Top 10 for LLM Applications, the MITRE ATLAS adversarial threat framework, and NIST’s AI Risk Management Framework.
This position is open to all candidates.