Senior Security Engineer, AI Red Team, Threat Operations

Overview

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. This role is responsible for executing Red Team operations across our AI portfolio, performing security research on novel attack surfaces, and developing automated solutions to scale offensive security capabilities.

You will work closely with security leadership, engineering teams, and researchers to validate security assumptions and drive meaningful improvements in our AI security posture.

As a Senior Security Engineer, you will be a hands-on technical contributor with deep expertise in offensive security and growing knowledge of AI/ML systems. You'll execute complex security assessments, discover vulnerabilities in AI infrastructure and applications, and translate technical findings into actionable recommendations. This position requires someone who can work independently on sophisticated technical challenges while collaborating effectively across teams to drive security outcomes.

• 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 the development of security metrics and reporting frameworks that demonstrate program effectiveness
• Support cross-organizational security initiatives to assess vulnerabilities introduced by growing reliance on AI

The Threat Operations team protects critical customer trust points through offensive security operations and emergent threat research. Our mission spans validating security across diverse technology landscapes, from AWS to satellite communications and autonomous systems to frontier AI models and advertising platforms. We simulate sophisticated threat actors, validate security assumptions, and identify novel risk patterns that drive meaningful security improvements. The team comprises security professionals with a cross-section of national security and private sector experience, providing a range of perspectives required for creative problem solving.

We value diversity of thought, creativity, and a strong Bias for Action and Earn Trust. We believe that there are no "perfect" security solutions and we develop and iterate using a continuous improvement process.

Diversity of experiences is valued. If you do not meet all qualifications, we encourage you to apply. If your career is just starting, or includes alternative experiences, don’t let it stop you from applying.

• Experience working in identifying security issues and risks, and developing mitigation plans
• Minimum 5+ years of experience in offensive security testing, penetration testing, or security research
• Hands-on experience with vulnerability discovery, exploitation, and lateral movement techniques
• Strong understanding of cloud security, network security, and application security principles
• Experience with scripting and automation using Python, Go, or similar languages

• 7+ years of experience in offensive security or related security engineering roles
• Experience with AI/ML security, including threats to AI systems, adversarial machine learning, or AI supply chain security
• Track record of building security tools or automation that scales across organizations
• Experience with Red Team operations, threat-based assessments, or security research programs
• Deep technical knowledge of cloud platforms (AWS, Azure, GCP) and container technologies
• Experience with distributed systems, training infrastructure, or inference optimization
• Demonstrated ability to translate complex technical findings into clear recommendations for diverse audiences
• Contributions to security research community through publications, presentations, or open-source tools
• Understanding of threat actor tradecraft and ability to emulate sophisticated attack techniques
• Experience working with cross-functional teams to drive security improvements

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status. Our inclusive culture empowers Amazonians to…