Senior AI/LLM Offensive Security Engineer - Remote

Horizon3; United States; Remote; USD 223,000 - 275,000; Full time

Benefits offered by this job

Remote work

Competitive compensation

Equity

Health, vision & dental insurance

Generous parental leave

Career growth opportunities

Job summary

Horizon3.ai is seeking a Staff Attack Engineer specializing in AI/LLM security to join our remote team. You will lead automated attacks inside NodeZero, translating research into scalable offensive tooling across AI systems and enterprise deployments.

This role emphasizes building repeatable attack patterns, operating with high ownership, and driving forward production-ready AI security capabilities in a fast-growing, remote environment.

Qualifications

• Expert-level Python and software engineering skills.
• Solid 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 offensive capabilities or tooling.
• Proven ability to break AI/LLM and agentic systems.
• Clear understanding of trust boundaries around AI tools, data sources, and permissions.

Responsibilities

• Break AI and agentic systems and translate research into automated attack modules.
• Design prompt injection and defense evasion attacks with reusable patterns.
• Conduct tool-use exploitation and credential/DTO access to expose attacker-like outcomes.
• Target AI infrastructure and model deployment pipelines in real-world environments.
• Research model and supply chain attack methods and map attack paths.
• Turn manual techniques into safe, scalable automation for NodeZero.

Skills

Python

Software engineering

Penetration testing

AI/LLM security

Security tooling

Tools

AWS Bedrock

Azure OpenAI

Neo4j

GCP Vertex AI

Job description

Horizon3.ai is seeking a Staff Attack Engineer specializing in AI/LLM security to join our remote team. You will lead automated attacks inside NodeZero, translating research into scalable offensive tooling across AI systems and enterprise deployments.

This role emphasizes building repeatable attack patterns, operating with high ownership, and driving forward production-ready AI security capabilities in a fast-growing, remote environment.