Artificial Intelligence Security Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an Artificial Intelligence Security Engineer based in the United States.

This fully remote role focuses on securing modern artificial intelligence and machine learning systems against emerging and sophisticated threats.You will design security controls, threat models, and incident response capabilities specifically for LLMs, AI applications, model APIs, and ML infrastructure.The role combines strong security engineering fundamentals with practical expertise in how AI systems are designed, deployed, and attacked.You will address challenges including prompt injection, model abuse, data exfiltration, adversarial machine learning, and AI supply chain risks.Working across application, cloud, identity, infrastructure, and AI security, you will help build resilient systems from the ground up.The position offers the opportunity to contribute to cutting-edge AI security practices in a collaborative technology environment.This is a full-time, direct W2 position that can be performed remotely from within the United States.

\n

Accountabilities:

• Design and implement security controls tailored to AI-powered applications, machine learning systems, LLMs, model APIs, and supporting infrastructure.

• Develop threat models and security architecture reviews for AI systems, identifying vulnerabilities, attack paths, and appropriate mitigation strategies.

• Assess and defend against AI-specific threats such as prompt injection, model abuse, adversarial machine learning, data exfiltration, and supply chain attacks.

• Apply established application security, identity, access management, cryptography, and cloud security principles to AI environments.

• Evaluate AI architectures, model deployment patterns, training data pipelines, APIs, and infrastructure for security risks.

• Develop and strengthen incident response capabilities for AI and ML-related security events.

• Collaborate with engineering, infrastructure, data science, and AI teams to embed security throughout the AI development and deployment lifecycle.

• Use Python and systems-level programming to develop security tooling, automation, testing capabilities, or defensive solutions.

• Conduct or support security assessments and red-team exercises against LLM-based products and AI-powered applications.

• Monitor emerging AI security research, attack techniques, vulnerabilities, and industry practices to continuously improve defensive capabilities.

• Contribute to security architecture standards, technical documentation, and recommendations for AI systems.

• Communicate complex security risks and mitigation strategies clearly to both technical and non-technical stakeholders.

Requirements:

• Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a related technical discipline.

• 6+ years of professional security engineering experience, including significant hands-on experience with AI or machine learning systems.

• Strong understanding of LLM internals, modern AI architectures, AI application patterns, and common model failure modes.

• Demonstrated experience designing and implementing security controls for AI-powered applications.

• Deep knowledge of application security, identity and access management, cryptography, and cloud security fundamentals.

• Practical experience with threat modeling and security architecture review methodologies.

• Familiarity with adversarial machine learning, prompt injection, model abuse, and other AI-specific attack techniques.

• Strong Python programming skills and proficiency in at least one systems programming language.

• Understanding of modern cloud infrastructure and associated security controls.

• Excellent written and verbal communication skills, with the ability to explain complex security concepts effectively.

• Experience with LLM red teaming, AI security research, or security-focused CTF participation is a plus.

• Publications, conference presentations, or open-source contributions related to AI security are advantageous.

• Familiarity with privacy-preserving machine learning techniques, including differential privacy, is desirable.

• Experience working with regulated industries or environments involving stringent data protection requirements is a plus.

• Work authorization: U.S. citizens, Green Card holders, EAD holders, and candidates eligible for H-1B transfer are encouraged to apply. New H-1B visa sponsorship is not available for this position.

Benefits:

• Salary: $80,000–$105,000 annually.

• Full-time, direct W2 employment.

• 100% remote work opportunity within the United States.

• Opportunity to work on emerging AI security challenges involving LLMs, machine learning, cloud infrastructure, and AI-powered applications.

• Career growth opportunities within a technology-focused environment.

• Exposure to cutting-edge AI security research, threat modeling, red teaming, and defensive engineering practices.

• Opportunity to contribute to innovative security tooling, methodologies, and AI security solutions.

• Equal employment opportunity and a commitment to an inclusive workplace.

\nHow Jobgether works:

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1