Senior Security Engineer, AI Application Security, Leo Security

About the role

The Leo Security team owns the security of product and operations of Amazon Leo end-to-end. We provide the necessary infrastructure and mechanisms to ensure the security of our satellite constellation and to protect the integrity and confidentiality of our customer data. Our team drives the research & development, deployment and operation of several mission-critical security systems and mechanisms.

Responsibilities

• Serve as the organization's AI security subject matter expert.
• Drive AI tool approval reviews, lead security reviews for AI-integrated systems, and make policy decisions on AI adoption.
• Represent security in cross-Amazon AI security working groups and drive cross-team alignment on AI policy direction.
• Mentor and backstop AI leads across teams on AI consultations and reviews.
• Define and drive implementation of proactive security controls for AI applications including GenAI-powered tools, agentic systems, and LLM-integrated services.
• Guide teams towards solutions that are secure by default; if secure-by-default solutions don't exist, invent and propose them.
• Develop and implement security controls for the AI software development lifecycle, ensuring builders build secure AI applications by default.
• Assess and drive mitigation of AI-specific security risks including prompt injection, model abuse, data exfiltration, unauthorized tool invocation, and autonomy boundary violations at scale.
• Establish environment-specific security bar, threat models, and defense priorities for AI systems.
• Construct security frameworks, rubrics, and runbooks for AI-related problem domains that enable others to apply your work in a repeatable way.
• Collaborate with builder teams to assess technical debt and risk in AI systems.
• Provide strategic direction that addresses vulnerabilities and fortifies our products.
• Lead the burn down of long-term AI security risk.
• Drive adoption of AI security guardrails, testing frameworks, and monitoring across the organization.
• Collaborate with business leaders to define AI security priorities.
• Support leaders by acting as a trusted advisor and providing direction that makes security easy.
• Help leaders measure their org's security execution.
• Work with builder teams to understand their build processes and ensure they use appropriate security linting, static analysis, and AI-specific testing tools.
• Instill a security culture in builder teams.
• Mentor builders who aspire to become security advocates and security engineers via 1-1 sessions and office hours.
• Assist Red Teams in identifying AI security testing priorities.
• Scope penetration tests for AI systems and help deep-dive on these engagements.
• Support security incident investigations related to AI systems, including prompt injection attacks, model misuse, and data exfiltration attempts.
• Investigate emerging AI security issues, root cause them, and devise mechanisms to prevent them.
• Propose a security vision for AI that delivers security and protects our customers.
• Leverage support from automation teams that find discoverable vulnerabilities.
• Advocate for the creation and deployment of new testing tools and detection mechanisms.
• And last of all—hack some really cool bleeding edge tech!

  Qualifications

  • 5+ years of any combination of the following: application security frameworks, identity and access controls, incident response, mobile security, cloud computing and security, AI security, threat intelligence, and penetration testing experience.
  • Demonstrated experience security-reviewing or architecting at least three of: AWS-hosted inference (Bedrock, IAM scoping, KMS, region/partition constraints), agentic systems (autonomy boundaries, prompt injection, tool-use mediation), MCP servers (data access patterns, registration/compliance, agentic MCP risk), model hosting infrastructure, 3P AI tool security review (data flow analysis, ingress/egress control, ECI/ITAR scoping).
  • 3+ years of hands-on AI/ML security work (security reviews of AI-integrated systems, threat modeling for AI tools, exposure to common AI architectures such as inference platforms, agentic systems, MCP/tool-use, and 3P AI tools).
  • Experience driving formal security reviews (ASR or equivalent) of complex AI systems through to certification, with comfort in risk-based review prioritization.
  • Knowledge of common AI security risks (prompt injection, data poisoning, model extraction, insecure tool use, autonomy boundary violations).
  • Demonstrated experience driving security policy decisions in cross-team or cross-org working group settings, comfortable navigating consensus among technical and non-technical stakeholders.
  • 5+ years of experience communicating complex technical concepts to non-technical audiences, with strong written and verbal skills and the ability to work effectively across internal and external organizations.