Senior AI Security Engineer II

Location: Onsite in New York, NY, United States

Company

Healthcare technology company building digital prescription-access and medication-delivery products that improve affordability, availability, and patient support.

What you will do

• Design and implement a multi-layer AI security framework covering data classification, detection and response, exfiltration prevention, governance, adversarial testing, and agentic identity management.
• Evaluate, deploy, and operate AI-specific security tooling within security operations.
• Architect secure MCP server deployments and define agent-to-agent authentication standards for agentic AI workflows.
• Establish AWS security guardrails for AI workloads and enforce PHI/PII handling controls.
• Lead AI red-team assessments and adversarial testing for privilege escalation, tool misuse, and unintended data access.
• Integrate AI security controls, automated testing, and validation pipelines into CI/CD and engineering workflows.

Requirements

• 7+ years of experience in security engineering with a strong understanding of software engineering processes.
• Hands-on experience with adversarial AI techniques, including prompt injection, model extraction, data poisoning, and evasion attacks.
• Knowledge of NIST AI RMF and ISO 42001 AI security frameworks.
• GitHub and Python skills for security tooling, evaluation harnesses, and automated AI system testing.
• Experience with enterprise AI platforms such as Claude Enterprise, OpenAI Enterprise, or Cursor.
• Excellent written and verbal communication skills.

Culture & Benefits

• Work on healthcare products affecting access to critical medications and patient outcomes.
• Collaborative, cross-functional environment spanning Engineering, Infrastructure, Data Science, and Product Security.
• Culture focused on continuous learning, curiosity, and practical innovation.
• Commitment to diversity and equal opportunity.