Principal Attack Engineer, AI/LLM

The role

You will define the long-term technical direction for AI/LLM offense and lead efforts to break AI and agentic systems. You will turn research into scalable, autonomous attack capabilities within the NodeZero platform.

What you will do

• Define the long-term technical vision for AI/LLM offense and its role in NodeZero and product strategy.
• Partner with senior leadership to shape priorities, investment decisions, and the AI/LLM roadmap.
• Set direction for complex, high-risk AI/LLM programs and establish decision principles.
• Lead cross-company initiatives across Attack Engineering, Platform, Product, and customer-facing teams.
• Diagnose systemic blockers in architecture, process, or technical capability.
• Define company-wide standards for reliability, safety, observability, and testing in LLM-powered systems.
• Develop P5 engineers and senior technical leaders.
• Own NodeZero's coverage strategy for the OWASP Top 10 for LLM Applications.
• Set the research and productization agenda for breaking AI and agentic systems.
• Set the long-term architecture for LLM-powered offensive applications and agentic workflows.

Required qualifications

• Exceptional Python and software engineering expertise.
• Deep experience designing secure, reliable, observable, and operable systems at scale.
• Deep expertise in offensive security, penetration testing, exploit development, or vulnerability research.
• Recognized expertise in AI/LLM and agentic-system security.
• Deep command of the OWASP Top 10 for LLM Applications and MITRE ATLAS.
• Track record of shipping high-impact security capabilities, platforms, or research programs.
• Ability to define long-term technical vision and drive execution through influence.
• Company-wide technical judgment regarding product value, safety, reliability, cost, and speed.
• Proven ability to develop senior technical talent.

Nice to have

• Experience setting technical direction or architecture across an engineering organization or multiple product areas.
• Industry-level contributions to AI security research through publications, talks, CVEs, or open-source projects.
• Experience shaping strategy for cloud AI platforms such as AWS Bedrock, AWS Agent Core, Azure OpenAI, or Google Vertex AI.
• Deep experience with agentic architectures, tool-use security, retrieval systems, vector databases, or graph databases.
• Background in traditional exploit development, vulnerability research, or building offensive security platforms at scale.
• CTF experience, particularly in AI/ML-focused challenge categories.
• A record of strengthening a company's technical credibility or market position through external leadership.

Benefits

• Equity package in the form of stock options
• Health, vision & dental insurance for you and your family
• Flexible vacation policy
• Generous parental leave

About the company

Horizon3 is a fast-growing, remote cybersecurity company dedicated to enabling organizations to proactively find, fix and verify exploitable attack vectors. Their flagship product is the NodeZero platform, which delivers autonomous pentests.