Remote AI Risk & Security Engineer

Bright-Vision-Technologies; United States; Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Risk Engineer to lead the design and implementation of security controls, threat models, and incident response capabilities tailored to AI/ML systems. This role focuses on prompt injection, model abuse, data exfiltration, and supply chain risks, with hands-on experience defending AI-powered applications and infrastructure.

The position is 100% remote within the Continental United States, offering strong career growth for a security-focused engineer

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a related discipline.
• Six+ years of security engineering experience, including AI/ML systems.
• Solid understanding of LLM internals and modern AI architectures.
• Hands-on experience designing security controls for AI-powered applications.
• Strong foundation in application security, identity, and cryptography.

Responsibilities

• Define and implement security controls targeting LLM and AI-powered risks.
• Build threat models for AI systems including prompt injection and data exfiltration.
• Design and deploy guardrails, content filters, and policy enforcement on model endpoints.
• Implement runtime detection and response for adversarial prompts and abuse.
• Secure training/fine-tuning pipelines with data provenance and access controls.
• Lead red-team exercises against AI systems and drive remediation.
• Evaluate third-party AI services and open-source AI components for security.

Skills

Python

Cloud security

Threat modeling

AI security

LLM internals

Cryptography

Communication

Adversarial ML

Education

BSc/MSc in CS/Cybersecurity

Tools

Python

Cloud platforms

Kubernetes

Job description

Bright Vision Technologies is seeking an AI Risk Engineer to lead the design and implementation of security controls, threat models, and incident response capabilities tailored to AI/ML systems. This role focuses on prompt injection, model abuse, data exfiltration, and supply chain risks, with hands-on experience defending AI-powered applications and infrastructure.

The position is 100% remote within the Continental United States, offering strong career growth for a security-focused engineer