Remote ML Security Engineer: AI/LLM Defenses Lead

Bright Vision Technologies; Centennial (CO); À distance; USD 100 000 - 150 000; Plein temps

Résumé du poste

Bright Vision Technologies is seeking an ML Security Engineer to lead the design and implementation of security controls, threat models, and incident response for AI/ML systems. This remote role requires a deep understanding of LLMs, model APIs, training data pipelines, and related risks.

You will collaborate with privacy, legal, and compliance teams, drive secure software practices, and stay current with adversarial ML research.

Qualifications

• Six or more years of security engineering experience.
• Experience with AI/ML systems and security controls.

Responsabilités

• Define security controls for LLM and AI risks.
• Build threat models for AI systems.
• Design guardrails and policy enforcement around model endpoints.
• Implement runtime detection for adversarial prompts.
• Secure training pipelines and data provenance.
• Lead red-team exercises on AI systems.
• Collaborate with privacy and compliance teams.
• Develop monitoring and incident response for AI workloads.

Connaissances

Python

Security engineering

Threat modeling

LLM security

Cloud security

Adversarial ML

Cryptography basics

Communication skills

Formation

Bachelor’s or Master’s degree in CS/Cybersecurity

Description du poste

Bright Vision Technologies is seeking an ML Security Engineer to lead the design and implementation of security controls, threat models, and incident response for AI/ML systems. This remote role requires a deep understanding of LLMs, model APIs, training data pipelines, and related risks.

You will collaborate with privacy, legal, and compliance teams, drive secure software practices, and stay current with adversarial ML research.