Red Team Associate Security Engineer II

What you'll do

• Develop and enhance security strategies, red teaming programs, and scalable technical solutions.
• Design secure AI and software architectures while reviewing code for adversarial resilience.
• Reduce AI and LLM vulnerabilities by implementing industry standards and emerging safety research.
• Conduct threat modeling and adversarial testing on generative AI, RAG pipelines, and ML systems.
• Provide guidance on secure design, logging, monitoring, and compensating controls for AI platforms.
• Define and implement AI red teaming methodologies, playbooks, and success metrics for model rollouts.
• Ensure secure infrastructure configuration in alignment with enterprise security architecture.
• Track emerging AI threats by engaging with external researchers, vendors, and standards bodies.

What we're looking for

• Formal training or certification in Public Cloud environment concepts is required.
• Advanced hands-on experience with cloud-native AI services like Bedrock is required.
• Experience with threat modeling, discovery, vulnerability, and penetration testing (e.g., MITRE ATLAS, OWASP Top 10 for LLMs) is required.
• Knowledge of foundational cybersecurity concepts such as IAM, Authentication, OIDC, and SAML is required.
• Practical experience with Infrastructure as Code solutions like Terraform and CloudFormation is required.
• Proficiency in Python scripting is required.
• Strong understanding of AI/ML concepts and knowledge of AI red teaming foundational concepts is required.
• Expertise in planning, designing, and implementing AI red teaming exercises for generative AI and LLMs (preferred).