Principal Attack Engineer, AI/LLM
Horizon3 AI1 day ago
Remote, United StatesStaff+
Base Salary
$238k - $280k/yr
Responsibilities
- Define Horizon3’s long-term technical vision, roadmap, architecture, and standards for AI/LLM offensive security capabilities.
- Lead cross-company initiatives involving Attack Engineering, Platform, Product, customer-facing teams, and other technical functions.
- Own NodeZero’s coverage strategy for the OWASP Top 10 for LLM Applications and extend it to multi-agent and tool-connected systems.
- Direct research into prompt injection, defense evasion, tool-use exploitation, context poisoning, remote code execution, data exfiltration, privilege escalation, poisoning, and related attack paths.
- Establish threat-modeling approaches for agentic systems covering trust boundaries, identities, permissions, tools, data sources, downstream systems, and business impact.
- Set technical direction for assessing AI infrastructure, including model serving, training pipelines, vector databases, GPU/MLOps tooling, and enterprise deployment architectures.
- Ensure AI/LLM security research becomes safe, reliable, scalable, production-grade NodeZero functionality.
- Guide LLM-powered offensive applications, agentic workflows, evaluation systems, microservices, and shared orchestration platforms.
- Set company-wide principles for cost, safety, hallucination guardrails, reliability, observability, evaluation quality, and operational risk.
- Partner with senior leadership on product decisions, investment, risk posture, roadmap priorities, and major architectural transformations.
- Develop P5 engineers and senior technical leaders while communicating with executives, technical leaders, and external stakeholders.
- Represent Horizon3 through technical writing, talks, research, or open-source contributions when appropriate.
Requirements
- Exceptional Python and software engineering expertise 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 research 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.
- Track record of shipping or shaping high-impact security capabilities, platforms, research programs, or technical standards across multiple teams.
- Ability to define long-term technical vision, resolve ambiguous company-wide problems, and drive execution through influence rather than direct authority.
- Strong technical judgment across product value, safety, reliability, cost, speed, and maintainability.
- Proven ability to develop senior technical talent and multiply an engineering organization’s mentorship capacity.
- Experience setting technical direction or architecture across an engineering organization or multiple product areas.
- Industry-level AI security research contributions through publications, conference talks, CVEs, open-source projects, or widely adopted techniques are preferred.
- Experience shaping strategy for AWS Bedrock, AWS Agent Core, Azure OpenAI, or Google Vertex AI is preferred.
- Deep experience with agentic architectures, tool-use security, retrieval systems, vector databases, graph databases such as Neo4j, or AI infrastructure security is preferred.
- Background in traditional exploit development, vulnerability research, or building offensive security platforms at significant scale is preferred.
- CTF experience, particularly in AI/ML-focused challenge categories, is preferred.
- A record of strengthening technical credibility, recruiting reach, or market position through external technical leadership is preferred.
Benefits
- Fully remote work with up to 10% travel required.
- Full-time roles are eligible for an equity package in the form of stock options.
- Health, vision, and dental insurance for employees and their families.
- Flexible vacation policy and generous parental leave.
- Career development opportunities in a collaborative, inclusive, and innovative environment.
- Hybrid and remote work models are supported depending on role and location, with some roles requiring regular presence at the Chicago office.
Tech Stack
Neo4jPython
Categories
About Horizon3 AI
Horizon3 AI builds NodeZero, a proactive security platform that autonomously performs penetration testing and validates attack paths across on‑prem, cloud, and hybrid environments. The company sells its software by subscription to security and IT teams at enterprises and government agencies, helping prioritize and verify fixes. Founded in 2019 and headquartered in San Francisco, it is privately held and serves customers across regulated industries and the public sector.