AI Security Lead

Role: AI Security Lead
Experience: 8+ years in Cybersecurity, with 2+ years in AI/ML Security or Advanced Application Security
Location: Pune
Role Overview:
We are looking for an experienced AI Security Lead to integrate security and Responsible AI controls throughout the AI lifecycle. The role involves identifying AI-specific threats, securing AI models and agents, implementing access controls, coordinating security testing, and ensuring compliance with security and risk requirements.
Key Responsibilities:
AI Threat Modelling: Identify and assess AI-specific security threats, vulnerabilities, and risks across the AI lifecycle.
AI Security Testing: Test for prompt injection, data leakage, and other LLM and AI agent vulnerabilities.
Identity & Access Management: Define agent and tool permissions and implement secure identity, secrets, and key management.
Responsible AI & Privacy: Implement data protection, privacy, Responsible AI, and risk management controls.
Security Assessments: Coordinate red teaming, penetration testing, and AI model and supply-chain risk assessments.
Risk & Compliance: Maintain risk registers, track remediation activities, and support security reviews and risk approvals.
Monitoring & Incident Response: Establish security logging, audit controls, incident response procedures, and operational security guidelines.
Requirements & Qualifications:
Experience: 8+ years in cybersecurity, including 2+ years in AI/ML security or advanced application security.
AI Security: Strong understanding of AI threat modelling, OWASP LLM/agent risks, and AI-specific vulnerabilities.
Azure AI Security: Familiarity with Azure AI Content Safety and related AI security controls.
IAM & Secrets Management: Experience with identity and access management, workload/agent identity, secrets, and key management.
Data Security: Knowledge of data loss prevention (DLP), privacy, and sensitive data protection.
Responsible AI: Understanding of model risk management and Responsible AI principles.
Security Testing: Experience with red teaming, penetration testing, and secure software development lifecycle (SDLC).
Monitoring & Response: Knowledge of security logging, audit mechanisms, and incident response.
Communication Skills: Strong stakeholder management skills and the ability to coordinate security and risk approvals.
Key Deliverables:
AI threat models and security control matrix
Security test plans and results
AI security risk register and remediation tracking
Operational security runbooks
👉 Interested? Share your CV at rudrakshi.jain@zidea.tech

Work arrangement
No