Description

Responsibilities

• Design, configure, and maintain security controls for GenAI and Agentic AI solutions in AWS, including AWS Bedrock Guardrails, content filtering, sensitive information redaction, token protection, and model access controls.
• Implement and operationalize runtime protection and detection for foundation models, agents, and cloud workloads.
• Develop and execute adversarial security tests targeting LLMs and AI agents, including prompt injection, jailbreaking, tool abuse, and data exfiltration scenarios.
• Partner with platform and engineering teams to deploy guardrails-as-code using Terraform or CloudFormation, embedding automated AI security checks into deployment pipelines.
• Configure logging, telemetry, and monitoring across AI services to pipe alerts into enterprise SOC platforms.
• Conduct threat modeling and security reviews for RAG architectures, agent orchestration frameworks, and tool integrations aligned with NIST AI RMF and MITRE ATLAS.

Qualifications

• Required
  • 5+ years of cloud experience with 1–2+ years in AI security.
  • Direct hands-on experience configuring AWS Bedrock Guardrails, model access policies, content moderation filters, and foundation model protections.
  • Strong proficiency with AWS core security (IAM, SCPs, AWS Organizations) and Infrastructure as Code (Terraform or CloudFormation).
  • Proven experience deploying and managing CrowdStrike Falcon, CrowdStrike AIDR, or equivalent cloud runtime detection platforms.
  • Deep technical understanding of RAG architectures, AI agent frameworks, prompt injection mitigations, output validation, and token abuse prevention.
  • Practical experience conducting security assessments and penetration tests specific to LLMs, tool integrations, and data leakage scenarios.
  • Experience integrating automated security gates and policy-as-code into continuous integration/continuous deployment pipelines.
  • Expertise in aggregating AI telemetry via Amazon CloudWatch, SIEM tools, or OpenTelemetry.
  • Bachelor's degree in Cybersecurity, Computer Science, Information Systems, Data Science, Engineering, or equivalent practical experience.
  • Proven ability to translate complex AI cybersecurity risks into actionable roadmaps for engineering teams and senior leadership.
  • Collaborative mindset with experience working in Agile, cross-functional delivery teams.
  • Strong critical-thinking skills to analyze emerging AI threat vectors and quickly adapt defense controls.
• Preferred
  • Advanced degree in a relevant field.
  • AWS Certified Security – Specialty.
  • AWS Certified AI Practitioner or AWS Cloud Practitioner.
  • CrowdStrike Falcon Platform Certifications (e.g., CCFA, CCFR).
  • CISSP, CCSP, or GIAC Cloud Security (GCSA/GPCS)

Key Skills

Education

Bachelor's degree