AI Security Engineer

View full description

Requirements:

• 7+ years of experience in information security, with 3+ years focusing on AI/ML systems
• Deep expertise in AI/ML security, including model security, data poisoning prevention, prompt injection guardrails, and privacy-preserving techniques
• Strong background in security architecture and threat modeling
• Experience implementing AI security controls in a regulated environment
• Advanced degree in Computer Science, Cybersecurity, or a related field
• Experience implementing Nvidia NeMo guardrails or similar LLM protect frameworks
• Knowledgeable in Amazon Bedrock, OpenAI APIs, Langchain, or similar AI model platforms
• Expertise in Python and modern software development practices
• Understanding of healthcare compliance (HIPAA, HITECH)
• Excellent analytical, problem-solving, and communication skills
• Ability to work independently to learn new technologies, processes, frameworks, and systems.

Responsibilities:

• Design and implement security architecture for AI systems, including LLMs and ML platforms
• Develop security standards and patterns for AI development and deployment
• Lead threat modeling for AI features
• Establish security controls for model training and monitoring
• Guide engineering teams on secure AI implementation patterns, including designing reusable multi-modal guardrails to protect against security, privacy, clinical, and brand threats
• Collaborate with product teams to evaluate security implications of new AI features
• Develop AI security testing tools including red team AI agents to test new features and models
• Lead incident response for AI-related security events
• Evaluate AI vendors and SaaS providers for security, compliance and data protection
• Assess emerging AI security tools and technologies
• Review cloud-based AI services for healthcare compliance
• Partner with legal and compliance teams ensure AI initiatives meet regulatory and contractual requirements
• Implement controls for data privacy, model integrity, and access management
• Develop metrics and reporting for AI security posture
• Liaison with customers and auditors on Omada’s approach to AI security and compliance