Sr AI Engineer, Security

News Corp () is seeking a senior AI security engineer to secure AI and agent platforms across AWS and GCP. This role focuses on guardrails, containment, supply chain integrity, detection and response, and threat modeling, while helping educate teams and lead AI security strategy.

Austin, TX, United States (Onsite)

• Secure the AI platform across AWS and GCP
  .
• Design and enforce guardrails for AI workloads on AWS (Bedrock, Lambda, IAM, KMS, SCPs, Guard Duty, Security Hub) and on GCP (Vertex AI, IAM, VPC Service Controls, Org Policies, Security Command Center, Cloud KMS).
• Define identification and authorization for agents and other non-human accounts using short-lived, narrowly scoped credentials
  , delegated user permissions
  , and a per-agent audit trail to limit blast radius from misbehavior.
• Build agent containment including separation of read and write permissions, network egress controls, sandboxed execution, approval gates for high-risk actions, and kill switches.
• Design an agent gateway or control plane that restricts agents and their tool calls to approved limits.
• Secure the AI supply chain by controlling model sources and scanning processes, including unsafe formats such as pickle; vet models and datasets from public hubs such as Hugging Face; manage an approval process for new MCP servers and agent tools; and maintain an inventory of the models, data, and tools used by each system (AI-BOM).
• Defend against prompt injection
  , tool poisoning,
  RAG poisoning
  , and sensitive data leakage.
• Implement detection and logging for agent and model activity and own AI-specific incident response playbooks
  .
• Lead threat modeling for new products, features, and internal solutions, applying frameworks such as STRIDE
  , the OWASP LLM/GenAI Top 10
  , MITRE ATLAS
  , and OWASP ASVS
  , and convert findings into design requirements and release criteria.
• Review pull requests and architecture designs for apps through agent fleets, providing concrete suggestions that move work forward.
• Develop paved-road secure-by-default frameworks
  , reference architectures, and templates to prevent whole categories of risk.
• Embed security into CI/CD through secrets scanning, SAST/SCA, Git Hub Actions hardening, and policy-as-code in Terraform.
• Run an ongoing red-team and evaluation program for models, agents, and LLM apps, testing new AI capabilities before launch.
• Partner with News Corp’s global cybersecurity team to align  AI and cloud security with group-wide standards, policies, and risk frameworks.
• Coordinate on incident response, threat intelligence, and vulnerability disclosure across News Corp businesses.
• Share AI security patterns, threat models, and lessons learned across the organization, and bring insights back to
• Build agents that support security work such as triaging findings, investigating alerts, auditing IAM for least privilege, and opening tested secure-by-default fix pull requests.
• Use Claude Code, Devin, and MCP to increase security team productivity and share these patterns with other engineering teams.
• Track emerging AI threats, incidents, research, and vendor capabilities, and translate them into actions for the platform.
• In major industry incidents, quickly assess potential exposure and lead response activities.
• Prototype new approaches when existing tools and best practices do not fit, run small experiments, measure outcomes, and standardize what works.
• Write short internal briefings on major developments and recommend when to adopt, pilot, or skip tools and practices.
• Create and deliver AI security training for engineers, product teams, and the wider company, covering prompt injection, data leakage, excessive agency, and secure use of Claude, Glean, Devin, and Gemini.
• Act as the security voice in AI…