Sr AI Security Engineer

Duties and Responsibilities:

• Perform security architecture reviews and threat modeling for AI-enabled applications.

• Conduct hands-on security testing of LLM, RAG, and agentic AI solutions.

• Identify vulnerabilities including prompt injection, sensitive-data exposure, insecure retrieval, excessive permissions, unsafe tool use, and authorization weaknesses.

• Assess security risks associated with AI agents, APIs, model integrations, vector databases, and third-party AI services.

• Partner with developers and AI engineering teams to design and implement practical security controls.

• Develop reusable security patterns and guardrails for common AI architectures.

• Build or automate security tests and tools used to evaluate AI applications.

• Help protect PHI, PII, credentials, and other sensitive information used by AI systems.

• Evaluate emerging AI security threats and translate relevant findings into engineering guidance.

• Support the organization's broader application security and secure AI development practices.

• Help ensure AI systems handling sensitive healthcare and enterprise information are designed with appropriate security and privacy controls.

• Assess how PHI, PII, and other sensitive information moves through prompts, models, APIs, retrieval systems, embeddings, vector stores, logs, agents, and downstream systems.

• Partner with privacy, compliance, legal, risk, and AI governance teams to translate requirements into practical technical controls.

• Support secure and responsible AI adoption consistent with organizational policies and applicable healthcare and regulatory requirements.

• Additional duties as required.

Minimum Qualifications:

• Technical Degree in Computer Science or Cyber Security and/or equivalent work experience

• Prior work Cyber Security work experience

• Experience in security engineering, vulnerability assessment, threat hunting, and incident response

• High School diploma or GED from an accredited institution

Preferred Qualifications:

• 5+ years of experience in application security, product security, security engineering, cloud security, offensive security, or a related technical security discipline.

• Strong understanding of application and API security, authentication, authorization, identity, data protection, and secure software development.

• Hands-on experience with security architecture reviews, threat modeling, vulnerability assessment, penetration testing, or security testing.

• Working knowledge of modern AI application architectures, including LLMs, model APIs, RAG, vector databases, and AI agents.

• Understanding of AI security risks such as prompt injection, data leakage, insecure output handling, excessive agency, and unsafe tool or API access.

• Programming or scripting experience, preferably Python.

• Experience working with cloud-based applications and services.

• Ability to communicate technical security risks and remediation recommendations effectively to engineering teams.

• Experience securing production generative AI or LLM applications.

• Experience with AI/LLM security testing or red teaming.

• Familiarity with agentic AI security, including tool permissions and least-privilege access.

• Familiarity with Model Context Protocol (MCP) security considerations.

• Experience with Azure OpenAI, AWS Bedrock, Google Vertex AI, or comparable AI platforms.

• Familiarity with OWASP guidance for LLM/GenAI applications, MITRE ATLAS, or NIST AI security guidance.

• Experience working with PHI, PII, or other sensitive data in a regulated environment.

• Experience integrating security testing into CI/CD or DevSecOps workflows.

• Experience with software supply-chain security and SBOM practices, including assessing third-party libraries, dependencies, models, prompts, and other AI application components for security risk.

• Experience designing secure tool and API consumption patterns for agentic AI, including authentication, authorization, least privilege, trust boundaries, credential management, and control of agent actions.

• Experience reviewing or implementing Infrastructure as Code (IaC) and applying security controls to cloud and AI infrastructure; experience with Terraform, Bicep, CloudFormation, or comparable frameworks preferred.

Compliance and Regulatory Responsibilities: See Above

• License/Certification: See Above

Hiring Range*:

Greater New York City Area (NY, NJ, CT residents): $134,600 - $194,480

All Other Locations (within approved locations): $119,600 - $177,905

As a candidate for this position, your salary and related elements of compensation will be contingent upon your work experience, education, licenses and certifications, and any other factors Healthfirst deems pertinent to the hiring decision.

In addition to your salary, Healthfirst offers employees a full range of benefits such as, medical, dental and vision coverage, incentive and recognition programs, life insurance, and 401k contributions (all benefits are subject to eligibility requirements). Healthfirst believes in providing a competitive compensation and benefits package wherever its employees work and live.

*The hiring range is defined as the lowest and highest salaries that Healthfirst in “good faith” would pay to a new hire, or for a job promotion, or transfer into this role.

WE ARE AN EQUAL OPPORTUNITY EMPLOYER. Applicants and employees are considered for positions and are evaluated without regard to mental or physical disability, race, color, religion, gender, gender identity, sexual orientation, national origin, age, genetic information, military or veteran status, marital status, mental or physical disability or any other protected Federal, State/Province or Local status unrelated to the performance of the work involved.