About the Role :

We are looking for an LLM Red Teaming Lead (AI Offensive Security Specialist) for a 6-month extendable contractual role. The ideal candidate should have strong expertise in AI/LLM security, red teaming, and adversary simulation, with hands-on experience in identifying and validating vulnerabilities in enterprise AI applications.

Key Responsibilities :

- Lead AI/LLM Red Teaming and Vulnerability Identification & Penetration Testing (VIPT) engagements.

- Design, execute, and manage security testing programs for AI and LLM applications.

- Simulate real-world attack scenarios against AI models and GenAI applications.

- Identify, exploit, and validate vulnerabilities in AI systems with high-confidence findings.

- Perform security assessments for MCP (Model Context Protocol) and AI Connectors.

- Build, improve, and maintain AI Model Validation Frameworks.

- Support the establishment of an AI Testing Center of Excellence (CoE).

- Ensure testing aligns with AI Governance, Risk, Compliance, and Security standards.

- Prepare detailed technical reports and executive-level security recommendations.

- Collaborate with cross-functional teams to improve AI security posture.

Required Skills :

- 7+ years of experience in Cyber Security, including 12 years in AI/LLM Security.

- Strong expertise in Red Teaming and Adversary Simulation.

- Hands-on experience in AI/LLM Security Testing and Offensive AI Security.

Strong understanding of :

1. Prompt Injection

2. Jailbreaking

3. Model Abuse

4. AI System Exploitation

5. LLM Attack Techniques

- Experience performing penetration testing for AI applications and GenAI platforms.

- Knowledge of AI governance, AI security frameworks, and model validation.

- Experience investigating and handling critical security incidents (P1).

- Strong analytical and problem-solving skills.

- Excellent written and verbal communication skills.

- Ability to independently lead client engagements.

Preferred Skills :

- Experience securing enterprise AI/GenAI deployments.

- Exposure to MCP (Model Context Protocol) security testing.

- Knowledge of OWASP Top 10 for LLM Applications and AI security best practices.

- Experience with cloud security and modern AI architectures.

Mandatory Requirements :

- Inactive UAN.

- LinkedIn Profile is mandatory.