Senior Security Engineer - AI Red Team

6d6 days ago

Amazon.com

Remote · Full-time · $178,400 – $226,700

About this role

We are looking for an experienced Senior Security Engineer to join our AI Red Team within Threat Operations. You will conduct sophisticated offensive security operations targeting AI systems, infrastructure, and emerging threats. Execute Red Team operations across our AI portfolio while performing security research on novel attack surfaces.

As a hands-on technical contributor with deep expertise in offensive security, execute complex security assessments on AI infrastructure and applications. Discover vulnerabilities and translate technical findings into actionable recommendations. Develop automated solutions to scale offensive security capabilities.

The Threat Operations team protects critical customer trust points through offensive security operations and emergent threat research. Simulate sophisticated threat actors across diverse landscapes from AWS to frontier AI models. Value diversity of thought, creativity, Bias for Action, and Earn Trust in a continuous improvement process.

Amazon Security values diverse experiences and encourages applications from non-traditional paths. Security is central to maintaining customer trust and delivering delightful experiences. Maintain a high bar for security across all Amazon products and services.

Requirements

Deep expertise in offensive security
Growing knowledge of AI/ML systems
Experience executing complex security assessments
Ability to discover vulnerabilities in AI infrastructure and applications
Hands-on experience with security testing on AI assets
Proficiency in developing automated tools for offensive security
Skill in analyzing findings and providing technical recommendations
Ability to collaborate across security, engineering, and research teams

Responsibilities

Conduct Red Team operations targeting AI assets including training pipelines, inference systems, model architectures, and supporting infrastructure
Perform offensive security research focused on threats to AI systems, AI supply chain security, and AI-enabled threat actor tradecraft
Discover and exploit vulnerabilities in AI infrastructure, applications, and supporting systems through hands-on security testing
Develop automated tools and solutions for threat emulation and scaling offensive security capabilities
Analyze security findings and provide detailed technical recommendations to engineering teams for remediation
Collaborate with security engineers and research scientists to advance AI security research and translate findings into practical risk insights
Simulate sophisticated threat actor techniques to validate detection and response capabilities
Contribute to security metrics and reporting frameworks that demonstrate program effectiveness