About this role
Assess and secure AI agents, tool integrations, and agentic workflows while designing and executing adversarial attack scenarios such as prompt injection and data leakage. Partner with AI engineers to establish automated security guardrails, audit AI Ops pipelines, vet third‑party AI supply chain components, and lead model risk assessments prior to production deployment.
Skills for this role
AI SecurityApplication SecuritySecurity EngineeringAgentic AIPrompt InjectionJailbreakingAdversarial Attack SimulationData Leakage PreventionRetrieval PipelinesAutomated Security GuardrailsVector Store Access ControlsOutput FilteringModel Risk AssessmentAI OpsMLOpsPythonPyTorchTensorFlowAgent Protocols (MCP)AI Red-TeamingPyRITGarakPromptfooCloud Security ArchitectureAWSAzureGCPContainer SecurityOWASP Top 10 for LLMsOWASP Agentic Threat Guidance (LLM)