---
title: 'Staff Attack Engineer, AI/LLM at Horizon3 AI'
canonical: 'https://feeny.ai/job/staff-attack-engineer-ai-llm-horizon3-ai-united-states-fsy83vfjzspz'
type: 'job'
last_seen: '2026-11-07'
---

# Staff Attack Engineer, AI/LLM at Horizon3 AI

- **Company:** [Horizon3 AI](https://feeny.ai/companies/horizon3-ai)
- **Location:** United States
- **Compensation:** $223k–$275k
- **Employment:** full-time
- **Work type:** remote
- **Posted:** 2026-04-10
- **Last confirmed live:** 2026-11-07
- **Apply:** https://jobs.ashbyhq.com/horizon3ai/94efbe91-1cdb-4875-99ec-a5680628d895/application

**Skills:** Python, Software Engineering, Penetration Testing, AI/LLM Security, OWASP Top 10 for LLMs, MITRE ATLAS, Prompt Injection, Defense Evasion, Tool Use Exploitation, Threat Modeling, LLM Applications, Microservices, Azure OpenAI, GCP Vertex AI, AWS Bedrock, AWS Agent Core, Graph Databases, Neo4j, CTF, AI Security Research

> The Staff Attack Engineer specializes in AI/LLM security, breaking down complex systems to create automated, scalable attack patterns for NodeZero's autonomous pentesting platform. This role involves designing prompt injection attacks, exploiting LLM agents, and building LLM-powered offensive capabilities while driv...

## Job description

Get to Know Us Horizon3 is a fast-growing, remote cybersecurity company dedicated to the mission of enabling organizations to proactively find and fix and verify exploitable attack vectors before criminals exploit them. Our flagship product, the NodeZeroTM platform, delivers production-safe autonomous pentests and other key assessment operations that scale across the largest internal, external, cloud, and hybrid cloud environments. NodeZero has been adopted by organizations of all sizes, from small educational institutions to government agencies and Global 100 enterprises. It is used by ITOps/SecOps teams, consulting pentesters, and MSSPs and MSPs. We are a fusion of former U.S. Special Operations cyber operators, startup engineers, and formerly frustrated cybersecurity practitioners. We're committed to helping solve our common security problems: ineffective security tools, false positives resulting in alert fatigue, blind spots, "checkbox” security culture, cybersecurity skills shortage, and the long lead time and expense of hiring outside consultants. Collectively, we are a team of learn it alls, committed to a culture of respect, collaboration, ownership, and results.

Summary We are hiring a Staff Attack Engineer specializing in AI/LLM security to join our team. You will break AI and agentic systems and turn that research into automated attacks inside NodeZero, our autonomous pentesting platform. This is not consulting or manual pentesting; the goal is to build repeatable, scalable attack patterns that run autonomously across customer environments. You’ll also help drive our LLM-powered offensive capabilities and act as a technical leader for AI/LLM offense.

Essential Functions Attacking AI/LLM Systems

- 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, focusing on generalized, reusable patterns.
- Conduct tool-use exploitation, abusing LLM agents’ access to code, file systems, APIs, and databases for attacker-realistic outcomes (e.g., context poisoning, RCE, data exfiltration, privilege escalation).
- Target AI infrastructure (model serving, training pipelines, vector databases, GPU/MLOps tooling) with an understanding of real-world enterprise deployments and misconfigurations.
- Research and apply model and supply chain attacks (poisoning, training data extraction, adversarial inputs, deployment pipeline abuse).
- Perform threat modeling for agentic systems, mapping trust boundaries and attack surfaces and turning them into concrete attack paths.
- Apply a strong productization mindset, turning manual techniques into safe, reliable, and scalable automated tooling.

Building with LLMs

- Build and extend LLM-powered applications (prompting, structured output, agentic workflows).
- Design with production concerns in mind: cost, safety and hallucination guardrails, reliability, and observability.
- Design and extend microservices that orchestrate LLM tasks and integrate with NodeZero and related offensive workflows.

Competencies / Requirements

- Expert-level Python and software engineering skills.
- Solid penetration testing fundamentals and understanding of common attack chains.
- Familiarity with AI/LLM security frameworks (e.g., OWASP Top 10 for LLMs, MITRE ATLAS).
- Experience in a security product or offensive security team, ideally 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, and how to systematically test and exploit them.
- Expert-level ownership – drives high-complexity, high-risk programs and sets strategy, not just execution.
- Self-motivated – identifies problems and builds solutions proactively.
- Industry obsessed – tracks the fast-moving AI security landscape and can speak to recent developments, new attacks, and where the field is heading.

Nice-to-Have

- Experience with other cloud AI services (e.g., Azure OpenAI, GCP Vertex AI).
- Contributions to AI security research (blog posts, conference talks, CVEs, open-source tools).
- Experience with AWS Bedrock and AWS Agent Core.
- Familiarity with graph databases (e.g., Neo4j).
- Background in traditional exploit development or vulnerability research.
- CTF experience, particularly in AI/ML-focused challenge categories.

## Perks of Horizon3

- Inclusive Team: We value diversity and promote an inclusive culture where everyone can thrive.
- Growth Opportunities: Be part of a dynamic and growing team with numerous career development opportunities.
- Innovative Culture: Work in a collaborative environment that encourages creativity and out-of-the-box thinking.
- Remote Work: We are a 100% remote company. Enjoy the convenience and work-life balance that comes with remote work.
- Competitive Compensation: We offer competitive salary, equity and benefits. Our benefits include health, vision & dental insurance for you and your family, a flexible vacation policy, and generous parental leave.

## Compensation and Values

At Horizon3, we believe that our people are our greatest asset, and our compensation philosophy reflects this core value. We are committed to fostering an environment where all employees feel valued, respected, and rewarded for their contributions. Our compensation structure is designed to be fair, competitive, and transparent, ensuring that every team member is recognized and compensated equitably across roles, levels, and locations. In accordance with various State’s transparency regulations, we provide the following salary range information for this position:

- Base salary range: $235,000 - $275,000 annually. The exact salary will be determined based on the selected candidate’s location, qualifications, experience, and relevant skills.
- Additional compensation: All full-time roles are eligible for an equity package in the form of stock options.

You Belong Here Horizon3 is not just an equal opportunity employer - we are a community that values diversity, equity, and inclusion as fundamental principles of our culture and success. We are dedicated to fostering a workplace where everyone feels welcome and respected, regardless of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity or expression, genetic information, marital status, or any other legally protected status by law. Our commitment to diversity and inclusion means we strive to attract, develop, and retain a workforce that reflects the varied communities we serve. We believe that diverse perspectives drive innovation and strengthen our ability to create cutting-edge cybersecurity solutions. At Horizon3, every team member is valued and supported in an environment that encourages personal and professional growth. We welcome candidates from all backgrounds and experiences, and we encourage all qualified individuals to apply. Come be a part of Horizon3, where your unique contributions are recognized, and your potential is limitless.

Other Duties Please note this job description is not designed to cover or contain a comprehensive listing of activities, duties or responsibilities that are required of the employee. Duties, responsibilities, and activities may change at any time with or without notice.

## About Horizon3 AI

## Company Overview
- **One-liner**: Horizon3.ai provides an autonomous penetration testing platform (NodeZero) that safely hacks production environments to identify and fix exploitable attack paths using AI.
- **Entity Type**: Private (Series D – latest funding round in 2026, led by Prosperity7 Ventures)
- **Headquarters**: San Francisco, California, United States (447 Battery Street, San Francisco, CA 94111)
- **Founded**: 2019
- **Founders**: Snehal Antani (Co-Founder & CEO); founded by a mix of US Special Operations, US National Security, and cybersecurity industry veterans

## Core Business
- **Primary industry**: Cybersecurity (autonomous penetration testing, vulnerability management, continuous security validation)
- **Target customers**: B2B – large enterprises, Fortune 100, government agencies (NSA, CISA), healthcare providers, financial services, manufacturing, education, public sector
- **Mission**: “Turn the map around” – using the attacker’s perspective to help enterprises prioritize defensive efforts. The company aims to shift the advantage from attackers to defenders by fighting AI with AI.

## Products & Services
- **[NodeZero®](https://horizon3.ai/)**: Autonomous penetration testing SaaS platform. Safely runs real attack techniques in production environments (no agents, no disruption). Discovers and chains exploitable vulnerabilities, misconfigurations, harvested credentials, and dangerous defaults across external, identity, on-prem, cloud, and Kubernetes attack surfaces. Also includes Active Directory password auditing and phishing impact testing. Continuously validates fixes and repeats autonomously.

## Market Standing
- **Valuation**: Not publicly disclosed
- **Key Metrics**: 
  - Annual Revenue: **$35.5M** (per LinkedIn)
  - Total Funding: **$187M** (per LinkedIn) / **$181M** (per CB Insights – conflicting reports; both cited)
  - **225,000+** production-safe tests completed
  - **5,000+** customers
- **Notable Investors/Partners**: 
  - SignalFire (lead in Seed, Series A, Series B)
  - Craft Ventures (lead Series C)
  - Prosperity7 Ventures (lead Series D – 2026)
- **Growth Signals**:
  - Ranked **#1 in Security** on the 2025 Inc. 5000 list
  - **#3 overall** on the 2025 Deloitte Technology Fast 500
  - Fast Company’s **Most Innovative Companies** (2026) – #1 in Security
  - Named to the **Fortune Cyber 60** (2023 & 2025)
  - Two-time **Black Unicorn Award** winner
  - Headcount grew **115.5% YoY** to 341 employees (LinkedIn)
  - Active job postings up **168.2% YoY**; operates in 14 countries

## Competitive Advantages
- **AI-driven autonomous testing** that learns from hundreds of thousands of tests and uses the right AI (ML, GenAI) for each problem – delivers evidence-based results with **zero hallucinations**.
- **Production-safe** – zero downtime across all production tests, trusted by the world’s most sensitive high-security environments (NSA, CISA, Fortune 10, major healthcare).
- **No agents required** – fully self-service SaaS, safe to run continuously.
- **Real attack techniques** – not a scanner; shows actual attacker paths and impact.
- **Rapid verification** – instantly confirms fixes and repeats the cycle, enabling a continuous validation loop.

## Strategic Focus
- **Continuous validation** – driving a loop of test-fix-verify-repeat autonomously.
- **Fighting AI with AI** – building NodeZero to operate at machine speed against AI-powered attacks.
- **Global expansion** – already in 14 countries, with active hiring in EMEA, APAC, and the Americas.
- **Scaling the team** – 59 active job postings (as of mid-2026), with emphasis on engineering, sales, and customer success roles.

## Why Work Here
- **Culture**: Rated **5.0/5.0 on LinkedIn** (76 reviews) with perfect scores for Culture (5.0), Career (4.9), Compensation (4.7), and Work-Life (4.6). Described as a “kick-ass organization hell bent on disrupting an industry” with a team of “motivated learn-it-alls.”
- **Work Policy**: Remote-friendly (most roles listed as remote, HQ in San Francisco, CA). Offers flexibility across time zones.
- **Notable Perks** (from Built In and LinkedIn):
  - Comprehensive healthcare (medical, dental, vision, FSA)
  - Life insurance, disability insurance
  - 401(k) with company matching
  - Equity and employee stock purchase plan
  - Generous parental leave and family medical leave
  - Performance bonuses
  - Job training, conferences, and customized development tracks
  - Promotion policies and career growth support
- **Engineering Culture**: Built by US Special Operations and National Security veterans. Emphasis on high autonomy, real-world impact, and cutting-edge AI/security work. “If you want to be part of a kick-ass organization hell bent on disrupting an industry and keeping attackers at bay, let’s talk.”

## Sources
1. [horizon3.ai – Homepage](https://horizon3.ai/)
2. [horizon3.ai – About/Team](https://horizon3.ai/about-us/)
3. [LinkedIn – Horizon3.ai Company Page](https://www.linkedin.com/company/horizon3ai)
4. [Built In – Horizon3.ai Careers & Perks](https://builtin.com/company/horizon3ai)
5. [CB Insights – Horizon3.ai Profile](https://www.cbinsights.com/company/horizon-3-ai)

## Other roles at Horizon3 AI

- [Director of Engineering, Threat Research](https://feeny.ai/job/director-of-engineering-threat-research-horizon3-ai-united-states-0fsq2qg04cee) — United States
- [Senior Attack Engineer, GCP](https://feeny.ai/job/senior-attack-engineer-gcp-horizon3-ai-united-states-p7dypj66skxv) — United States
- [Senior Attack Engineer, Kubernetes](https://feeny.ai/job/senior-attack-engineer-kubernetes-horizon3-ai-united-states-8bbsrmqpg924) — United States
- [Senior Attack Engineer, OCI](https://feeny.ai/job/senior-attack-engineer-oci-horizon3-ai-united-states-06y0k0t6a5p9) — United States
- [Staff Backend Engineer, Internal](https://feeny.ai/job/staff-backend-engineer-internal-horizon3-ai-united-states-eccvzb53mpb7) — United States
- [Senior Sales Engineer (SLED)](https://feeny.ai/job/senior-sales-engineer-sled-horizon3-ai-united-states-agqan5xzy6d6) — United States
- [Research Staff, Adversarial Intelligence](https://feeny.ai/job/research-staff-adversarial-intelligence-horizon3-ai-united-states-xxx9ghesv6ha) — United States
- [Engineering Manager, Internal Attack](https://feeny.ai/job/engineering-manager-internal-attack-horizon3-ai-united-states-tx9j8q1pkfsx) — United States
- [Senior Account Executive, SLED - New York](https://feeny.ai/job/senior-account-executive-sled-new-york-horizon3-ai-new-york-2d49m7hyp482) — New York, NY
- [Senior Account Executive, SLED - Texas](https://feeny.ai/job/senior-account-executive-sled-texas-horizon3-ai-united-states-nkhqvten2p1s) — United States