AI Security Architect: Secure ML Platforms & Threat Modeling

GAC Solutions; Jersey City (NJ); On-site; USD 140,000 - 200,000; Full time

Job summary

GAC Solutions in Jersey City, NJ seeks a security architect to design and review secure architectures for AI/ML platforms, LLM applications, and secure deployment pipelines. You'll embed security into MLOps, CI/CD, and IaC, and collaborate with engineering to implement risk-based controls.

You will conduct threat modeling for prompt injection, data leakage, and model risk; manage IAM, encryption, and logging; review third-party models and tools for privacy and compliance; and build monitoring

Qualifications

• Strong background in cybersecurity, cloud security, application security, DevSecOps, or technology risk.
• Experience securing cloud-native platforms, APIs, microservices, containers, Kubernetes, CI/CD pipelines, and infrastructure-as-code.
• Strong AWS cloud security exposure or comparable hyperscaler security depth, including IAM, encryption, network controls, logging, secrets, and secure deployment patterns.
• Understanding of AI/ML and GenAI-specific risks such as prompt injection, adversarial attacks, data leakage, model misuse, retrieval poisoning, model supply-chain risk, and unsafe tool use.
• Familiarity with threat modeling, vulnerability management, security testing, incident response, secure SDLC, DevSecOps, and Terraform/IaC controls.

Skills

Cybersecurity

Cloud security

Application security

DevSecOps

Threat modeling

Incident response

Security testing

Tools

Terraform

Kubernetes

AWS

CI/CD tooling

Job description

GAC Solutions in Jersey City, NJ seeks a security architect to design and review secure architectures for AI/ML platforms, LLM applications, and secure deployment pipelines. You'll embed security into MLOps, CI/CD, and IaC, and collaborate with engineering to implement risk-based controls.

You will conduct threat modeling for prompt injection, data leakage, and model risk; manage IAM, encryption, and logging; review third-party models and tools for privacy and compliance; and build monitoring