Required Skills: Cisco Certifications , ATLAS , Cloud Security , Agile , Amazon Web Services , Artificial Intelligence , Data Integrity , CISSP
Job Description
The candidate will focus on AI guardrails, safety classifiers, and adversarial and red-team testing utilizing OWASP Agentic Top 10, OWASP LLM Top 10, and MITRE ATLAS framework standards. The role involves securing MLOps, ensuring model provenance and training-data integrity, as well as managing SPIFFE/SPIRE identity, OPA authorization, and multi-agent trust controls. Additionally, the role encompasses deploying and tuning open-weight models, implementing MCP servers, and driving secure SDLC across cloud security platforms.
Technical Capabilities & Requirements:
- AI guardrails and safety classifiers.
- Adversarial and red-team testing using OWASP Agentic Top 10, OWASP LLM Top 10, and MITRE ATLAS.
- MLOps security, model provenance, and training-data integrity.
- SPIFFE/SPIRE identity and OPA authorization.
- Multi-agent trust controls.
- Proficiency with AI platforms, LLMs, GenAI agents, and MCP.
- Strong understanding of cloud security, secure SDLC, and DevSecOps.
- Building GenAI agents and implementing MCP servers.
- Deploying and tuning open-weight models.
- Effective use of cybersecurity tools for standard security functions.
- AWS Security Specialty or equivalent certification required.
- CISSP or CCSP certification preferred.