Red Team Associate Security Engineer II

What you'll do

• Design secure AI and software architectures that ensure adversarial resilience and prevent malicious behavior.
• Conduct threat modeling and adversarial testing on generative AI, RAG pipelines, and ML systems.
• Develop and implement AI red teaming methodologies, playbooks, and success metrics for continuous testing.
• Reduce AI and LLM vulnerabilities by evolving security policies, testing protocols, and controls.
• Provide guidance on secure design, logging, monitoring, and compensating controls for AI platforms.
• Build internal tools, dashboards, and automation to support red teaming activities.
• Ensure secure infrastructure configuration in alignment with enterprise security architecture and cloud-native services.
• 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.
• Advanced hands-on experience with cloud-native AI services like Bedrock.
• Experience with threat modeling, discovery, vulnerability, and penetration testing.
• Knowledge of foundational cybersecurity concepts such as IAM, Authentication, OIDC, and SAML.
• Practical experience with Infrastructure as Code solutions like Terraform and CloudFormation.
• Proficiency in Python scripting.
• Strong understanding of AI/ML concepts and AI red teaming foundational concepts.
• Expertise in planning and implementing AI red teaming exercises for generative AI and LLMs (preferred).