Position Summary...
What you'll do...
- Review internal AI projects, pipelines, and architectures for security gaps, and drive mitigations.
- Analyze emerging global threats and risks related to AI, and update our security policies, playbooks, and standards accordingly.
- Define and refine scalable security processes and controls for AI and Agentic systems across their lifecycle.
- Collaborate with engineers and product teams to implement secure-by-default patterns in CI/CD and MLOps workflows.
- Build reference implementations and prototypes to validate security controls in real-world AI environments.
- Act as a mentor and trusted advisor on secure engineering and AI safety topics..
- Drive continuous improvement by adopting emerging technologies and industry standards within the security domain.
- Python programming skills securing agent execution environments, validate and sanitize structured model outputs/tool calls, or arbitrary execution in dynamic evaluation workflows.
- Experience integrating automated AI security testing—prompt injection, model scanning and dependency vulnerability checks.
- Experience isolating autonomous agent runtimes and untrusted tool executions using hardened container environments.
- Best practices to audit, track, and enforce peer review for system prompts, agent tool schemas, and policy-as-code, preventing prompt tampering.
- Proficiency in defining immutable, secure Linux environments for AI workloads, configuring runtime guardrails, OS-level sandboxing
- Knowledge of multi-agent design patterns, state management, and blast-radius containment, ensuring agents operate safely within deterministic boundaries
- Stock
ㅤ
Minimum Qualifications...
Outlined below are the required minimum qualifications for this position. If none are listed, there are no minimum qualifications.
Preferred Qualifications...
Outlined below are the optional preferred qualifications for this position. If none are listed, there are no preferred qualifications.
Primary Location...