About the Role
We are seeking a highly skilled AI Security Engineer to design, implement, and maintain security controls for AI/ML applications and Large Language Model (LLM) deployments. The ideal candidate will possess deep expertise in AI security, cloud security, threat detection, and infrastructure automation, with hands-on experience in securing AI workloads on Google Cloud Platform (GCP).
Key Responsibilities
- Design and implement security controls for AI/ML platforms, including Large Language Models (LLMs).
- Identify, assess, and mitigate AI-specific threats such as prompt injection, data leakage, model poisoning, adversarial attacks, and unauthorized model access.
- Develop and maintain threat detection mechanisms and response procedures for AI applications.
- Define detection criteria, tune security controls, and effectively manage false positives.
- Implement and manage security infrastructure using Terraform and Infrastructure as Code (IaC) practices.
- Build security automation and monitoring solutions using Python.
- Collaborate with AI/ML, Cloud, and Security teams to ensure secure development and deployment of AI solutions.
- Conduct security assessments, reviews, and risk analyses for AI projects.
Required Qualifications (Must Have)
AI Security
- Deep understanding of AI/ML security concepts and challenges.
- Strong knowledge of security threats specific to Large Language Models (LLMs).
Project Experience
- Proven hands-on experience implementing and managing security for AI projects.
- Ability to articulate architecture, security controls, challenges, and outcomes from previous AI security implementations.
Threat Detection & Response
- Experience defining threat detection criteria, incident response processes, and handling false positives effectively.
Terraform
- Hands-on experience with Terraform for provisioning and managing cloud security infrastructure.
Python
- Strong Python programming skills for security automation, integrations, and AI/ML-related development.
Google Cloud Platform (GCP)
- Strong hands-on experience with GCP services, cloud security controls, IAM, networking, logging, and monitoring.
Preferred Qualifications (Nice to Have)
Model Armor
- Knowledge and practical understanding of Model Armor or similar AI security protection frameworks.
- Experience implementing AI-specific security layers and configuring threat detection policies for AI applications.
