Staff AI Security Engineer

Blink Health

10d

About The Position

Blink Health is seeking a Senior AI Security Engineer to lead the security, governance, and risk management of AI at BlinkRx. This role will cover enterprise AI tools and agentic AI pipelines. The individual contributor will architect and operate a comprehensive AI security program, drive policy and technical controls, lead red-teaming and adversarial testing, and act as an internal expert on AI-specific threats. The ideal candidate will possess deep security engineering expertise combined with practical knowledge of modern AI systems, cloud-native architectures, and software engineering practices. This role requires close collaboration with Engineering, Infrastructure, Data Science, and Product Security teams to ensure secure, responsible, and scalable deployment of AI technologies.

Requirements

7+ years of experience in Security Engineering with a sound understanding of the Software Engineering process.
Hands-on experience with adversarial AI techniques including prompt injection, model extraction, data poisoning, and evasion attacks.
Understanding of AI security frameworks: NIST AI RMF, ISO 42001.
GitHub and Python skills for security tooling, evaluation harnesses, and automated testing of AI systems.
Demonstrated experience with Enterprise AI platforms such as Claude Enterprise, OpenAI Enterprise, Cursor, etc.
Excellent written and verbal communication skills.

Responsibilities

Design and implement a multi-layer AI security framework spanning data classification, detection and response, exfiltration prevention, governance, adversarial testing, and agentic identity management.
Evaluate, deploy, and operate AI-specific security tooling and integrate them into BlinkRx's security operations.
Architect secure MCP (Model Context Protocol) server deployments and define agent-to-agent authentication standards for agentic AI workflows.
Partner with Cloud Security to establish guardrails in AWS for AI workloads.
Define and enforce PHI/PII handling controls for all AI systems.
Design and execute AI red-team assessments against AI applications.
Integrate AI security controls into CI/CD pipelines and engineering workflows.
Develop automated testing and validation for AI applications and AI pipelines.
Build and operate an AI security testing pipeline using tools.
Perform adversarial testing of agentic AI workflows for privilege escalation, tool misuse, and unintended data access patterns.