Principal Attack Engineer, AI/LLM

Horizon3

8d•$238,000 - $280,000•Remote

About The Position

Horizon3 is hiring a Principal Attack Engineer specializing in AI/LLM security to define the long-term technical direction for AI/LLM offense. The role leads complex efforts to break AI and agentic systems and turn research into scalable, autonomous attack capabilities in NodeZero, Horizon3’s autonomous pentesting platform. The focus is on LLM-based applications, including chatbots, copilots, RAG pipelines, and AI agents used by employees, customers, and the public. This is a product and technical leadership role rather than consulting or manual pentesting. The position operates across company strategy and technical direction. It shapes the vision for AI/LLM offensive capabilities, informs major technical and product decisions with senior leadership, and establishes architecture, standards, and organizational alignment for multiple teams. The role sets the research and productization agenda, develops repeatable attack frameworks, and ensures research becomes safe, reliable, scalable product capability. It also establishes architecture and operating principles for LLM-powered applications and agentic workflows integrated with NodeZero. Horizon3 is a fully remote cybersecurity company. The job may require up to 10% travel. The base salary range is $238,000–$280,000, determined by location, qualifications, experience, and relevant skills. Full-time roles are eligible for stock options. Benefits include health, vision, and dental insurance for employees and their families, a flexible vacation policy, and generous parental leave.

Requirements

Exceptional Python and software engineering expertise, including experience designing secure, reliable, observable, and operable 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 and translating them into durable technical strategy.
Deep command of the OWASP Top 10 for LLM Applications and MITRE ATLAS, with the judgment to extend beyond existing frameworks.
A track record of shipping or shaping high-impact security capabilities, platforms, research programs, or technical standards across multiple teams.
Demonstrated ability to define long-term technical vision, resolve difficult ambiguous problems, and drive execution through influence rather than direct authority.
Company-wide technical judgment to make consequential tradeoffs across product value, safety, reliability, cost, speed, and maintainability.
Proven ability to develop senior technical talent and multiply an engineering organization’s mentorship capacity.
Self-motivated, highly credible, and deeply engaged with the direction of the AI security industry.

Nice To Haves

Experience setting technical direction or architecture across an engineering organization or multiple product areas.
Industry-level contributions to AI security research through influential publications, conference talks, CVEs, open-source projects, or widely adopted techniques.
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, graph databases such as Neo4j, or AI infrastructure security.
Background in traditional exploit development, vulnerability research, or building offensive security platforms at significant scale.
CTF experience, particularly in AI/ML-focused challenge categories.
A record of strengthening a company’s technical credibility, recruiting reach, or market position through external technical leadership.

Responsibilities

Define the long-term technical vision for AI/LLM offense and its role in NodeZero and the company’s broader product strategy.
Partner with senior engineering, product, and business leadership to shape priorities, investment decisions, risk posture, and the roadmap for AI/LLM offensive capabilities.
Set direction for complex, high-risk, and business-critical AI/LLM programs, including outcomes and decision principles for execution.
Lead cross-company initiatives requiring alignment across Attack Engineering, Platform, Product, customer-facing teams, and other technical functions.
Diagnose and resolve systemic blockers in architecture, process, operating models, or technical capabilities.
Define company-wide standards for reliability, safety, observability, evaluation, testing, cost management, and operational readiness in LLM-powered offensive systems.
Develop P5 engineers and other senior technical leaders and strengthen the organization’s capacity to deliver AI/LLM security capabilities.
Communicate with executives, technical leaders, and external stakeholders, and guide the organization through major technical transitions.
Own NodeZero’s coverage strategy for the OWASP Top 10 for LLM Applications and define areas beyond the list, particularly for multi-agent and tool-connected systems.
Set the research and productization agenda for breaking AI and agentic systems, balancing technical opportunity, customer impact, safety, and strategic differentiation.
Identify novel, high-leverage attack classes and establish frameworks, abstractions, and coverage models that make them repeatable in NodeZero.
Direct the approach to prompt injection, defense evasion, tool-use exploitation, context poisoning, remote code execution, data exfiltration, privilege escalation, and other agentic attack paths.
Set technical direction for assessing AI infrastructure, including model serving, training pipelines, vector databases, GPU/MLOps tooling, and enterprise deployment architectures.
Evaluate model and supply-chain attack risks, including poisoning, training-data extraction, adversarial inputs, and deployment-pipeline abuse, and determine how the company should respond.
Establish threat-modeling approaches for agentic systems that account for trust boundaries, identities, permissions, tools, data sources, downstream systems, and business impact.
Ensure research becomes safe, reliable, and scalable product capability rather than isolated expertise or one-off demonstrations.
Serve as the internal technical authority on novel AI/LLM offensive problems and, where appropriate, represent the company through technical writing, talks, research, or open-source contributions.
Set the long-term architecture for LLM-powered offensive applications, agentic workflows, evaluation systems, and integration with NodeZero.
Establish principles for cost, safety, hallucination guardrails, reliability, observability, evaluation quality, and operational risk.
Guide the architecture of microservices and shared platforms that orchestrate LLM tasks across offensive workflows.
Lead architectural transformations when existing approaches cannot support the company’s scale, product ambitions, or safety requirements; document the vision and build organizational support.
Promote strong ownership, incident learning, measurable quality standards, and sustainable technical practices for operating and improving these systems over time.