Remote AI Risk Engineer — Secure AI Systems

Bright Vision Technologies; Franklin, Brentwood, Nashville (TN, TN, TN); Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies seeks an AI Risk Engineer to design and implement security controls for AI/ML systems, addressing prompt injection, data exfiltration, and model abuse. You will build threat models, guardrails, and runtime defenses while securing training pipelines and multi-tenant AI services.

The role emphasizes collaboration with privacy, legal, and compliance to meet regulatory obligations and stay current with adversarial ML research.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or related discipline.
• Six or more years of security engineering experience, including AI/ML systems.
• Strong understanding of LLM internals, modern AI architectures, and failure modes.
• Hands-on experience designing security controls for AI-powered applications.
• Deep knowledge of application security, identity, and cryptography fundamentals.
• Experience with threat modeling and security architecture review processes.
• Familiarity with adversarial ML, prompt injection, and model abuse research.
• Proficiency in Python and at least one systems language.
• Strong understanding of cloud security and modern infrastructure controls.
• Excellent written and verbal communication skills.

Responsibilities

• Define and implement security controls targeting LLM and AI risks.
• Build threat models for AI systems, including prompt injection and data exfiltration.
• Design guardrails, content filters, and policy enforcement around model endpoints.
• Implement runtime detection and response for adversarial prompts.
• Secure training and fine-tuning pipelines, including data provenance and access controls.
• Design controls for data handling, retention, and redaction in LLM workflows.
• Lead red-team exercises against AI systems and drive remediation.
• Evaluate hardening of third‑party AI services and open‑source components.
• Implement identity, authorization, and tenant isolation for multi‑tenant AI services.
• Drive supply chain security for ML artifacts and dependencies.
• Collaborate with privacy, legal, and compliance teams to meet regulations.
• Develop monitoring, logging, and detection strategies for AI workloads.
• Lead incident response for AI-specific security events.
• Stay current with adversarial ML and emerging regulatory developments.

Skills

Security engineering

Python

Cloud security

Threat modeling

AI/ML systems

Cryptography fundamentals

Communication skills

Education

Bachelor’s or Master’s degree in Computer Science or Cybersecurity

Tools

Python

Cloud security tools

Threat modeling tools

Cryptography libraries

Job description

Bright Vision Technologies seeks an AI Risk Engineer to design and implement security controls for AI/ML systems, addressing prompt injection, data exfiltration, and model abuse. You will build threat models, guardrails, and runtime defenses while securing training pipelines and multi-tenant AI services.

The role emphasizes collaboration with privacy, legal, and compliance to meet regulatory obligations and stay current with adversarial ML research.