Senior AI Security Engineer II

BlinkRx; New York (NY); On-site; USD 180,000 - 230,000; Full time

Job summary

BlinkRx is hiring a Senior AI Security Engineer II to lead security, governance, and risk management of AI across the enterprise. This role focuses on building a comprehensive AI security program, implementing controls, and testing AI systems and pipelines to prevent data exposure and misuse.

The ideal candidate will combine security engineering depth with practical AI system knowledge, partnering with Engineering, Infrastructure, Data Science, and Product Security to deploy secure, scalable AI

Qualifications

• 7+ years in Security Engineering or equivalent.
• Experience with adversarial AI techniques (prompt injection, data poisoning, evasion).
• Knowledge of AI security frameworks (NIST AI RMF, ISO 42001).
• Proficiency in Python and security tooling; familiarity with enterprise AI platforms.

Responsibilities

• Design and implement a multi-layer AI security framework across data, governance, and response.
• Evaluate and operate AI security tooling and integrate into security operations.
• Architect secure MCP server deployments and agent authentication for AI workflows.
• Partner with Cloud Security to safeguard AWS AI workloads.
• Lead AI red-team assessments and CI/CD security integration.
• Develop automated testing and validation for AI systems and pipelines.
• Conduct adversarial testing of agentic AI workflows.

Skills

Security engineering

Adversarial AI

NIST AI RMF

ISO 42001

Python

GitHub workflows

Communication

Tools

OpenAI Enterprise

Claude Enterprise

Cursor

Job description

Blink Health is the fastest growing healthcare technology company that builds products to make prescriptions accessible and affordable to everybody. Our two primary products -- BlinkRx and Quick Save -- remove traditional roadblocks within the current prescription supply chain, resulting in better access to critical medications and improved health outcomes for patients.

BlinkRx is the world's first pharma-to-patient cloud that offers a digital concierge service for patients who are prescribed branded medications. Patients benefit from transparent low prices, free home delivery, and world-class support on this first-of-its-kind centralized platform. With BlinkRx, never again will a patient show up at the pharmacy only to discover that they can't afford their medication, their doctor needs to fill out a form for them, or the pharmacy doesn't have the medication in stock.

We are a highly collaborative team of builders and operators who invent new ways of working in an industry that historically has resisted innovation. Join us!

We are hiring a Senior AI Security Engineer II to lead the security, governance, and risk management of AI at BlinkRx, from enterprise AI tools used by our workforce to the agentic AI pipelines being built by our engineering teams. This is an individual contributor role with high organizational visibility and impact.

You will architect and operate a comprehensive AI security program, drive policy and technical controls across the AI lifecycle, lead red-teaming and adversarial testing of AI systems, and serve as the internal expert on AI-specific threats including prompt injection, model inversion, data poisoning, and agentic identity abuse.

The ideal candidate combines deep security engineering expertise with practical knowledge of modern AI systems, cloud-native architectures, and software engineering practices. This individual will partner closely with Engineering, Infrastructure, Data Science, and Product Security teams to ensure AI technologies are deployed securely, responsibly, and at scale.

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.

Qualifications:

• 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.

Why Join Us:

It is rare to have a company that both deeply impacts its customers and is able to provide its services across a massive population. At Blink, we have a huge impact on people when they are most vulnerable: at the intersection of their healthcare and finances. We are also the fastest growing healthcare company in the country and are driving that impact across millions of new patients every year. Our business model not only helps people, but drives economics that allow us to build a generational company. We are a relentlessly learning, constantly curious, and aggressively collaborative cross-functional team dedicated to inventing new ways to improve the lives of our customers.

We are an equal opportunity employer and value diversity of all kinds. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.

Applicants who provide their phone number and consent to receive text messages may receive SMS or MMS updates from Blink Health regarding their application.