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 for AI and ML systems, including LLMs and model APIs.

You will address prompt injection, data exfiltration, and supply chain risks, deploying guardrails, monitoring, and durable defenses across AI workflows and infrastructure.

Qualifications

• Six or more years of security engineering experience, including AI/ML.
• Strong understanding of LLM internals and AI architectures.
• Experience designing security controls for AI-powered applications.
• Proficiency in Python and at least one systems language.
• Cloud security and infrastructure controls knowledge.
• Threat modeling and security architecture reviews.

Responsibilities

• Define security controls for LLM and AI risks.
• Build threat models for AI systems, including prompt injection and data exfiltration.
• Design guardrails and policy enforcement for model endpoints.
• Implement runtime detection and response for adversarial prompts.
• Secure training and fine-tuning pipelines and data provenance.
• Lead red-team exercises against AI systems and drive remediation.
• Collaborate with privacy, legal, and compliance teams.
• Develop monitoring and detection strategies for AI workloads.
• Lead incident response for AI security events.
• Stay current with adversarial ML and regulatory developments.

Skills

Security engineering

AI/ML systems

LLM internals

Threat modeling

Python

Systems language

Cloud security

Communication

Education

Bachelor’s or Master’s in CS/Cybersecurity

Tools

Open-source AI tooling

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 for AI and ML systems, including LLMs and model APIs.

You will address prompt injection, data exfiltration, and supply chain risks, deploying guardrails, monitoring, and durable defenses across AI workflows and infrastructure.