AI Security Engineer: Risk & Defense for LLMs (Remote)

Socket.dev; Columbus, Dublin (OH, OH); On-site; 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 for AI/ML systems, covering model endpoints, data pipelines, and deployment infra.

The role focuses on threats such as prompt injection, data exfiltration, and supply chain risks, with hands-on work across threat modeling, incident response, and red-team exercises to strengthen AI security posture.

Qualifications

• Bachelor’s or Master’s degree in CS, Cybersecurity, or related field.
• 6+ years of security engineering experience, incl. AI/ML systems.
• Strong understanding of LLM internals and AI architectures.
• Experience designing security controls for AI-powered applications.

Responsibilities

• Define and implement security controls specifically targeting LLM and AI-powered application risks.
• Build threat models for AI systems, including prompt injection, jailbreaks, data exfiltration, and abuse patterns.
• Design and deploy guardrails, content filters, and policy enforcement layers around model endpoints.
• Implement runtime detection and response capabilities for adversarial prompts and abusive behavior.
• Secure training and fine‑tuning pipelines, including data provenance, integrity, and access controls.
• Design controls for sensitive data handling, retention, and redaction in LLM workflows.
• Lead red‑team exercises against AI systems and drive remediation of identified weaknesses.
• Evaluate and harden third‑party AI services and open‑source AI components used internally.
• Implement identity, authorization, and tenant-isolation patterns for multi‑tenant AI services.
• Drive supply chain security for ML artifacts including weights, datasets, and inference dependencies.
• Collaborate with privacy, legal, and compliance teams to ensure AI systems meet regulatory obligations.
• Develop monitoring, logging, and detection strategies tailored to AI workloads.
• Lead incident response for AI‑specific security events and drive durable improvements.
• Stay current with adversarial ML, LLM security research, and emerging regulatory developments.

Skills

Security engineering

Threat modeling

Python

Systems languages

Cloud security

AI/ML security knowledge

Communication skills

Education

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

Job description

Bright Vision Technologies is seeking an AI Risk Engineer to lead the design and implementation of security controls for AI/ML systems, covering model endpoints, data pipelines, and deployment infra.

The role focuses on threats such as prompt injection, data exfiltration, and supply chain risks, with hands-on work across threat modeling, incident response, and red-team exercises to strengthen AI security posture.