Horizon3.ai

3 months ago

Staff Attack Engineer, AI/LLM

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 4 hours agoStatus: Live

Job Summary

Staff Attack Engineer specializing in AI/LLM security responsible for breaking AI and agentic systems, translating research into automated, repeatable attack modules in NodeZero, and driving offensive capabilities for AI/LLM. You will design prompt injection, conduct tool-use exploits, attack AI infrastructure, research model and supply-chain attacks, and shape threat modeling for enterprise deployments in a fully remote, security-focused product environment.

Location: United States

Workplace: Remote

Employment Type: Full time

Job Function: Data Science & Machine Learning

Key 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, focusing on generalized, reusable patterns.
•Conduct tool-use exploitation, abusing LLM agents’ access to code, file systems, APIs, and databases for attacker-realistic outcomes.
•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).

Pay and Benefits

Perks:Remote WorkHealth InsuranceVisionDentalParental Leave

Key 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.

Experience:CybersecurityAi security

Skills:Self-motivationOwnershipProactivityProblem-solvingCommunication

Languages:English

Tech Stack:PythonLLM securityOWASP Top 10 for LLMsMITRE ATLASVector databasesGPUMLOpsCloud

Company Brief

Horizon3.ai

Builds NodeZero®, an autonomous penetration-testing platform that continuously finds, prioritizes, and verifies exploitable vulnerabilities across on-premises, cloud, and hybrid environments to help organizations reduce security risk.

Industry: Cybersecurity

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Funding: Series D

Headquarters: San Francisco, United States

Founded: 2019

Glassdoor: 4.9

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

Horizon3.ai

3 months ago

Staff Attack Engineer, AI/LLM

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 4 hours agoStatus: Live

Job Summary

Location: United States

Workplace: Remote

Employment Type: Full time

Job Function: Data Science & Machine Learning

Key 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, focusing on generalized, reusable patterns.
•Conduct tool-use exploitation, abusing LLM agents’ access to code, file systems, APIs, and databases for attacker-realistic outcomes.
•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).

Pay and Benefits

Perks:Remote WorkHealth InsuranceVisionDentalParental Leave

Key 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.

Experience:CybersecurityAi security

Skills:Self-motivationOwnershipProactivityProblem-solvingCommunication

Languages:English

Tech Stack:PythonLLM securityOWASP Top 10 for LLMsMITRE ATLASVector databasesGPUMLOpsCloud

Company Brief

Horizon3.ai

Industry: Cybersecurity

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Funding: Series D

Headquarters: San Francisco, United States

Founded: 2019

Glassdoor: 4.9

Website LinkedIn Glassdoor