AI Security Engineer

Interra Health•Boston, MA

3d•Remote

About The Position

Interra Health is expanding its use of artificial intelligence and machine learning across a fast-moving, highly regulated healthcare market. As an AI Security Engineer on the Security Engineering team, reporting to the Lead Security Engineer, you will help secure the models, data pipelines, and AI solutions. This role is hands-on and technical: you will assess AI systems for vulnerabilities, build guardrails against risks like prompt injection and data leakage, and partner with Engineering and Data & Analytics to bake security into how AI is designed and shipped. You will independently assess and resolve AI security risks across multiple workflows, escalating complex or high-impact issues to senior security leadership as appropriate. The right person is genuinely curious about how AI systems can fail, and wants to build the guardrails before something goes wrong, not after.

Requirements

Bachelor's degree and 5+ years in security engineering or application security, including hands-on experience securing AI/ML systems or LLM-based applications
Deep knowledge of AI/ML security risks (including the OWASP Top 10 for LLMs, adversarial ML, and data poisoning) and proven ability to test for and mitigate them
Hands-on experience with security tooling, including SAST/DAST and vulnerability scanning, and comfort scripting in Python or a similar language
Understanding of cloud infrastructure (AWS, Azure, or GCP) and how AI/ML workloads are deployed and secured within it
Clear communicator who can translate technical risk into terms non-security stakeholders understand
Comfort operating in a fast-paced, post-merger environment where systems, priorities, and structures are still evolving

Nice To Haves

Experience securing systems in a regulated healthcare or life sciences environment (e.g., HIPAA, HITRUST)
Familiarity with LLM security frameworks and tools, such as MITRE ATLAS, Garak, or promptfoo
Security certifications such as OSCP, GCIH, or CISSP
Experience red-teaming or penetration-testing AI/ML systems specifically

Responsibilities

Lead security assessments of AI/ML models, data pipelines, and AI-enabled applications, identifying vulnerabilities such as prompt injection, model inversion, data poisoning, and adversarial inputs
Partner with Data & Analytics and Engineering to embed security requirements and threat modeling into the AI development lifecycle, from data collection through model deployment
Build and maintain guardrails, monitoring, and detection controls for AI systems in production, flagging anomalous model behavior and unauthorized data access
Conduct security reviews of third-party AI tools, APIs, and vendors, such as LLM providers, before they are integrated into Interra Health
Lead incident response for AI-related security events, including investigating suspicious model outputs or unexpected data exposure
Design and advise on standards for the secure, responsible use of AI, including data handling practices for training and inference
Test and validate access controls, encryption, and data segmentation for AI systems
Use AI tools to accelerate security testing, code review, and threat research, while modeling responsible AI use for the broader engineering organization
Stay current on the evolving AI threat landscape and translate emerging risks, such as jailbreaks and model-supply-chain risks, into practical mitigations
Document findings, risk assessments, and remediation plans clearly for both technical and non-technical stakeholders