AI Security Specialist

Role & responsibilities

• Assess and identify vulnerabilities, risks, and threats across AI/ML and Generative AI solutions.
• Perform AI security reviews, threat modeling, risk assessments, and security testing for AI applications.
• Design and implement security controls to protect AI models, training data, prompts, APIs, and AI infrastructure.
• Ensure confidentiality, integrity, and availability of AI systems and data.
• Monitor AI environments for security incidents, anomalies, and potential cyber threats.
• Investigate security breaches, perform root cause analysis, and drive remediation activities.
• Develop and enforce AI security standards, policies, governance frameworks, and best practices.
• Collaborate with AI engineers, architects, developers, cybersecurity teams, and business stakeholders to embed security throughout the AI lifecycle.
• Evaluate and mitigate AI-specific risks such as prompt injection, model poisoning, data leakage, adversarial attacks, and unauthorized model access.
• Ensure compliance with enterprise security, privacy, regulatory, and Responsible AI requirements.
• Support secure deployment practices, DevSecOps integration, and production readiness reviews.
• Create security documentation, risk reports, architecture reviews, playbooks, runbooks, and audit evidence.
• Track security findings, vulnerabilities, risks, and remediation activities through closure.
• Contribute to continuous improvement of AI security posture, governance processes, and security monitoring capabilities.
• Provide technical guidance and knowledge sharing on AI security controls, emerging threats, and industry best practice

Preferred candidate profile

• 6 to 8 years of experience in Cyber Security, Application Security, Cloud Security, or AI Security.
• Hands-on experience in securing Generative AI (GenAI), LLM, AI/ML, and Agentic AI solutions.
• Strong knowledge of AI threat modeling, AI risk assessment, vulnerability management, and AI governance.
• Experience in identifying and mitigating Prompt Injection, Model Poisoning, Data Leakage, Adversarial Attacks, Jailbreaking, and Unauthorized Model Access.
• Working knowledge of OWASP Top 10, OWASP LLM Top 10, MITRE ATLAS, Responsible AI, and Secure AI Development Practices.
• Experience with AI platforms such as Azure OpenAI, Azure AI Services, AWS Bedrock, Amazon SageMaker, Google Vertex AI, Gemini, or OpenAI.
• Strong understanding of DevSecOps, Secure SDLC, API Security, IAM, Data Protection, Encryption, and Cloud Security Controls.
• Hands-on experience with Security Monitoring, SIEM, Incident Response, Threat Hunting, and Security Operations.
• Experience performing security reviews, architecture assessments, compliance audits, and penetration testing activities.
• Familiarity with compliance and governance frameworks such as ISO 27001, SOC2, NIST AI RMF, GDPR, HIPAA, or PCI-DSS.
• Strong stakeholder management, documentation, communication, and Agile delivery experience.