Our client is a fast-growing cybersecurity company building security infrastructure for AI systems. They're hiring a Principal AI Security Researcher to lead and scale their AI security research and red-teaming function.
Highly technical leadership role. Candidate should have spent significant time attacking, evaluating, and securing modern AI systems. Sits at the intersection of offensive security, adversarial AI research, and applied engineering.
What you'll be doing
- Lead and grow teams focused on AI red teaming, adversarial research, and AI security engineering
- Design and execute advanced attacks against LLMs, GenAI applications, AI agents, and multi-agent systems
- Research prompt injection, jailbreaks, indirect prompt injection, tool abuse, agent manipulation, data exfiltration, model misuse, adversarial behavior
- Build automated systems for continuous AI security testing and adversarial evaluation
- Establish methodologies and infrastructure for testing AI systems at scale
- Lead research into emerging attack surfaces across agent orchestration, tool use, and multi-agent protocols
- Translate research into guardrails, detection mechanisms, monitoring, and security controls
- Partner with engineering and product to build security into AI systems through the development lifecycle
- Define AI security testing frameworks informed by OWASP, MITRE ATLAS, NIST AI RMF
- Shape technical roadmap and long-term research strategy for the company's AI security platform
- Represent the company externally through research, publications, conferences
- Significant experience leading security research, offensive security, AI security, or R&D teams
- Deep hands-on expertise in AI red teaming, adversarial ML, LLM security, or GenAI security
- Strong understanding of how modern AI systems are built, attacked, evaluated, deployed
- Practical experience researching or exploiting vulnerabilities in LLMs, AI applications, or agentic systems
- Experience building security testing frameworks, offensive tooling, automated evaluations, adversarial testing infrastructure
- Comfortable operating at strategic and technical level, close enough to the research to challenge assumptions
- Track record building high-performing technical teams and taking research from concept to implementation
- Strong communication across engineering, product, security, and executive stakeholders
- 5+ years across cybersecurity, AI security, ML security, adversarial research, or related field
- Published AI security or adversarial ML research
- Conference presentations (Black Hat, DEF CON, OWASP events)
- Open-source AI security contributions, standards, or research communities
- Built automated red-teaming or adversarial evaluation platforms
- Developed AI guardrails, runtime security systems, anomaly detection, AI monitoring infrastructure
- Hands-on experience with agentic frameworks and multi-agent orchestration
- Experience securing AI workloads across major cloud environments
- Background in AI trust & safety, adversarial ML, offensive security, or AI research
- Experience evaluating frontier models or complex AI/agentic systems in production
