AI Risk Engineer — TalentHop, United States

This is a Fully Remote Job

About Our Client:

The organization operates in the technology consulting and software development sector, delivering cloud, AI, data, and enterprise solutions across the United States. It addresses the growing need for advanced technology services within various industries, helping clients leverage cutting-edge AI and data capabilities.

About the Opportunity:

The AI RISK ENGINEER role is focused on leading the design and implementation of security controls, threat models, and incident response strategies specifically for AI and machine learning systems. This position plays a crucial role in mitigating unique security challenges associated with large language models, model APIs, training data pipelines, and AI-powered applications, thereby strengthening the organization's AI infrastructure and application security.

Responsibilities:

• Define and implement security controls targeting risks in large language models and AI applications.

• Develop threat models addressing prompt injection, jailbreaks, data exfiltration, and abuse patterns.

• Design and deploy guardrails, content filters, and policy enforcement around AI model endpoints.

• Implement runtime detection and response for adversarial prompts and abusive behaviors.

• Secure training and fine-tuning pipelines, ensuring data provenance, integrity, and access controls.

• Establish controls for sensitive data handling, retention, and redaction within AI workflows.

• Lead red-team exercises on AI systems and remediate identified vulnerabilities.

• Evaluate and strengthen third-party AI services and open-source AI components.

• Implement identity, authorization, and tenant-isolation for multi-tenant AI services.

• Manage supply chain security for machine learning artifacts including weights, datasets, and inference dependencies.

• Collaborate with privacy, legal, and compliance teams to ensure regulatory compliance.

• Develop monitoring, logging, and detection strategies tailored to AI workloads.

• Lead incident response for AI-specific security events and drive long-term improvements.

• Stay informed on adversarial machine learning, large language model security research, and emerging regulations.

Requirements:

• Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or related field.

• Six or more years of security engineering experience, including significant AI or ML security work.

• Strong understanding of large language model internals, AI architectures, and failure modes.

• Experience designing security controls for AI-powered applications.

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

• Proficiency in threat modeling and security architecture review.

• Familiarity with adversarial machine learning, prompt injection, and model abuse.

• Proficiency in Python and at least one systems programming language.

• Strong understanding of cloud security and modern infrastructure controls.

• Excellent written and verbal communication skills.

Pay Range and Compensation Package:

• Salary range from $100,000 to $150,000 annually.

Equal Opportunity Statement: Our client is an equal opportunity employer. They celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, or national origin.

Note:

TalentHop is a recruitment partner of this role. Please note that all employment decisions, including candidate assessment, interviews, hiring, compensation, and employment terms, are made exclusively by the hiring employer.