: LLM Red Teaming Lead (AI Offensive Security Specialist)

Experience: 7+ Years (including 1–2 years in AI/LLM Security)

Location: Remote

Shift Timing: India Shift (IST)

Job Overview

We are looking for an experienced LLM Red Teaming Lead (AI Offensive Security Specialist) with solid expertise in Red Teaming, Adversary Simulation, and AI/LLM Security. The candidate should have hands-on experience in offensive AI testing, identifying vulnerabilities in AI/LLM systems, and leading security testing engagements.

Required Skills and Qualifications

- Strong experience in Red Teaming and Adversary Simulation.
- Hands-on expertise in AI/LLM Security and Offensive AI Testing.
- Deep understanding of LLM attack vectors, including:
- Prompt Injection
- Model Abuse
- Jailbreaking
- AI System Exploitation

Key Responsibilities

- Lead LLM Red Teaming (VIPT) engagements.
- Design and execute AI model security testing programs.




- Simulate real-world attacks against AI/LLM systems.
- Support the development of an AI Testing Center of Excellence (CoE).
- Build and enhance Model Validation Frameworks.
- Perform MCP/Connector Security Testing.
- Align testing activities with AI Governance and Security requirements.
- Identify and validate genuine vulnerabilities with a focus on high-confidence findings.

Key Expectations

- Strong client-facing and stakeholder management skills.
- Ability to lead engagements independently.
- Experience handling critical security incidents (P1 Tickets).
- Excellent verbal and written communication skills.
- Ability to deliver high-quality technical and executive-level outputs.

Share your updated resume at [email protected]

📌 LLM Red Teaming Lead (AI Offensive Security Specialist) (India)
🏢 truelancer staffing
📍 India