Horizon3AI
Principal Attack Engineer, AI/LLM
$238K–$280K
US, Remote · Remote · Principal · Full-time · Posted Oct 30, 2026
About the job
Defines company-wide technical direction for AI/LLM offensive security and turns research into reliable, scalable attack capabilities within NodeZero.
What you'll do
- Set the AI/LLM offensive security vision, architecture, standards, and roadmap across teams.
- Direct research and coverage for attacks on LLM applications, agentic systems, and supporting AI infrastructure.
- Develop senior technical talent and guide cross-company execution of production-grade LLM-powered offensive systems.
What they ask for
- Exceptional Python and software engineering expertise building secure, reliable, observable systems at scale.
- Deep expertise in offensive security, penetration testing, exploit development, vulnerability research, or a closely related discipline.
- Recognized expertise in AI/LLM and agentic-system security, including identifying novel attack paths.
- Deep command of the OWASP Top 10 for LLM Applications and MITRE ATLAS.
Nice to have
- Industry-level contributions to AI security research, such as publications, talks, CVEs, or open-source projects.
- Experience with cloud AI platforms, agentic architectures, retrieval systems, vector databases, or AI infrastructure security.
Pay
$238,000 - $280,000 USD base salary
Tools
Python, NodeZero, OWASP Top 10 for LLM Applications, MITRE ATLAS, AWS Bedrock, AWS Agent Core, Azure OpenAI, Google Vertex AI
AI focus
Leads offensive security research and product development for LLM applications and agentic systems, including attack coverage, threat modeling, AI infrastructure assessment, and safe, reliable LLM-powered offensive workflows.
Model-written summary · the original posting is authoritative