Staff AI Security Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Create and implement a comprehensive multi-layer AI security framework that includes data classification, detection and response, exfiltration prevention, governance, adversarial testing, and agentic identity management.

• Assess, deploy, and manage AI-specific security tools, integrating them into BlinkRx's security operations.

• Design secure deployments of MCP (Model Context Protocol) servers and establish authentication standards for agent-to-agent interactions within agentic AI workflows.

• Collaborate with the Cloud Security team to set up protective measures in AWS for AI workloads.

• Establish and maintain controls for handling PHI/PII for all AI systems.

• Plan and execute red-team assessments focused on AI applications.

• Incorporate AI security measures into CI/CD pipelines and engineering processes.

• Create automated testing and validation processes for AI applications and pipelines.

• Develop and manage an AI security testing pipeline utilizing various tools.

• Conduct adversarial testing of agentic AI workflows to identify privilege escalation, tool misuse, and unintended data access patterns.

⛳️ Requirements

• Over 7 years of experience in Security Engineering with a solid grasp of the Software Engineering lifecycle.

• Practical experience in adversarial AI techniques, including prompt injection, model extraction, data poisoning, and evasion attacks.

• Familiarity with AI security frameworks such as NIST AI RMF and ISO 42001.

• Proficiency in GitHub and Python for developing security tools, evaluation harnesses, and automating testing of AI systems.

• Proven experience with Enterprise AI platforms including Claude Enterprise, OpenAI Enterprise, and Cursor.

• Strong written and verbal communication abilities.

🏝️ Benefits

• Health insurance

• 401(k)

• Paid time off

• Remote work options