Act as the primary subject matter expert for Generative AI and Agentic AI security, providing technical guidance on secure design, model hardening, and privacy-preserving architectures.
Conduct deep-dive threat modeling and risk assessments for complex AI systems, specifically addressing risks like prompt injection, model inversion, and supply chain attacks.
Perform and/or support specialized security testing, assessments and adversarial simulations on AI models and agentic workflows to identify vulnerabilities.
Define and support the implementation of security guardrails, best practices, and custom tooling to ensure secure AI development at scale.
Monitor and analyze security events and AI system logs to detect anomalous or unauthorized behavior in generative and agentic systems including oversight over unauthorized access to sensitive company data.
Research and stay current with the latest security controls, threats and vulnerabilities in AI.
Collaborate with cross-functional teams to ensure that privacy and security are primary considerations in AI development and operation across CWGS.
Work with senior analysts and engineers to investigate and respond to security incidents and provide recommendations for remediation.

Requirements

7+ years of experience in information security, with a proven track record in Application Security, Cloud Security, or Product Security.
A bachelor's degree in information systems or equivalent work experience; an M.B.A. or M.S. in information security is preferred.
Expertise in securing autonomous AI agents throughout their lifecycle including definition, development, and operations within major enterprise ecosystems including Microsoft Copilot Studio, Google Vertex AI Agent Builder, Claude (Anthropic), Perplexity, Amazon Bedrock AgentCore, and OpenAI’s Operator agentic modes.
Experience implementing Model Context Protocol (MCP) for secure tool integration, designing robust guardrails to prevent prompt injection or goal hijacking, and enforcing the principle of least privilege across agentic identity and access management (IAM).
Proficiency in securing cloud environments (Azure, AWS or GCP) and leveraging modern security technologies such as SIEM and CSPM tools.
Familiarity with industry-standard security frameworks (NIST AI RMF, OWASP Top 10 for LLMs, CIS, or ISO).
Strong ability to translate complex AI security risks into actionable remediation steps for non-security engineering teams.
Excellent verbal and written communication skills.
Demonstrated ability to work effectively in a fast-paced, cross-functional team environment.
A passion for protecting users and their data.
Professional certifications such as CISSP, CompTIA Security+, or specialized AI/Cloud security certifications.
Experience with incident response procedures.

Benefits

Paid Time Off
401(k)
Employee Assistance Program
Good Sam Roadside Assistance
Discounts
Paid parental leave (if eligibility is met)
Tuition Reimbursement (if eligibility is met)
On the job training opportunities
Comprehensive benefit package including medical, dental, vision and more!

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

Generative AI securityAgentic AI securitythreat modelingrisk assessmentssecurity testingadversarial simulationsModel Context Protocol (MCP)cloud securityidentity and access management (IAM)incident response

Soft Skills

communication skillscollaborationproblem-solvingability to work in fast-paced environmentstranslating complex riskstechnical guidancepassion for data protection

Certifications

CISSPCompTIA Security+AI security certificationsCloud security certifications