Employer description & source details
Threat model new AI agent features before launch: direct and indirect prompt injection, jailbreaks, data exfiltration through agent outputs, and over-privileged tool use Design guardrails for agentic workflows: least-privilege tool and connector scopes, human-in-the-loop approvals for high-risk actions, and output filtering Enforce tenant and data isolation across retrieval (RAG), context stores, and model calls, so no customer’s data leaks into another’s context Secure the AI supply chain: model and provider vetting, third-party MCP servers and connectors, prompt and config versioning Run AI red-team exercises and build automated adversarial tests (prompt injection suites) into CI Security baselines for Kubernetes and cloud infrastructure: RBAC, network policies, workload identity, secrets management, per-tenant network isolation Security in CI/CD: IaC scanning, SAST and dependency scanning, policy-as-code guardrails AI-aware detection with our current technology and tooling: logging prompts, tool calls and agent actions, and alerting on anomalous agent behavior Partner with the Security & Compliance Lead on technical controls and evidence for SOC 2 Type II, ISO 27001, HIPAA and ISO 42001, plus the NIST AI RMF 5+ years in cloud security, application security, or DevSecOps (GCP/Azure Preferred) Deep hands-on Kubernetes and cloud security experience Security automation with IaC (Terraform/Helm) and Python or Bash. A working understanding of LLM application risks (OWASP Top 10 for LLM Applications) and how agentic systems fail Comfortable influencing engineers without formal authority Hands-on experience securing LLM, RAG, or agentic systems in production AI red teaming, or familiarity with MITRE ATLAS CNAPP/CSPM tooling, SIEM/detection engineering Contributions to AI sec
Extracted skills: python, azure, gcp, kubernetes, terraform, recruiting, security, devsecops