Staff AI/LLM Offensive Security Engineer

Aimlroles; Northern (KY); Hybrid; USD 235,000 - 275,000; Full time

Benefits offered by this job

Remote work

Competitive compensation

Equity package

Health, vision & dental insurance

Flexible vacation policy

Parental leave

Job summary

Horizon3 is hiring a Staff Attack Engineer specializing in AI/LLM security to join our team. You will break AI and agentic systems and turn research into automated attacks inside NodeZero, our autonomous pentesting platform.

This role focuses on building repeatable, scalable attack patterns that run autonomously across customer environments and driving our LLM-powered offensive capabilities with technical leadership.

Qualifications

• Expert-level Python and software engineering skills.
• Strong penetration testing fundamentals and attack chains.
• Familiarity with AI/LLM security frameworks (OWASP Top 10 for LLMs, MITRE ATLAS).
• Experience in a security product or offensive security team with shipped capabilities.
• Proven ability to break AI/LLM and agentic systems.

Responsibilities

• Break AI and agentic systems and translate that research into automated, repeatable attack modules for NodeZero.
• Design and execute prompt injection and defense evasion attacks with reusable patterns.
• Exploit tools and LLM agents to demonstrate attacker-realistic outcomes (RCE, exfiltration).
• Target AI infrastructure and enterprise deployments, including GPUs and pipelines.
• Research model and supply chain attacks and map attack surfaces to concrete paths.
• Threat model agentic systems and convert findings into tests and tooling.
• Productize techniques into safe, scalable automated tooling.

Skills

Python

Penetration testing

AI/LLM security

Security product experience

Offensive security

Tools

OWASP Top 10 for LLMs

MITRE ATLAS

Job description

Horizon3 is hiring a Staff Attack Engineer specializing in AI/LLM security to join our team. You will break AI and agentic systems and turn research into automated attacks inside NodeZero, our autonomous pentesting platform.

This role focuses on building repeatable, scalable attack patterns that run autonomously across customer environments and driving our LLM-powered offensive capabilities with technical leadership.