AI Red Team Engineer / AI Security Specialist

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Red Team Engineer / AI Security Specialist based in India.

This is a high-impact security role focused on identifying and addressing vulnerabilities across enterprise AI systems.

You will challenge LLMs, RAG architectures, AI agents, APIs, and integrations to uncover weaknesses before they can be exploited.

Your work will span prompt injection, jailbreaks, guardrail bypasses, data leakage, privacy, access control, and unauthorized agent actions.

You’ll combine offensive security thinking with practical AI expertise to assess how intelligent systems behave under adversarial conditions.

The role also involves automating security testing, documenting findings, and helping drive effective remediation.

You’ll work across environments supporting industries such as banking, finance, audit, semiconductor, and technology.

This opportunity is ideal for a security-minded engineer who wants to help establish stronger and more resilient standards for enterprise AI.

Accountabilities:

• Conduct red-team assessments of LLMs, Retrieval-Augmented Generation (RAG) systems, AI agents, and other generative AI applications.
• Test AI systems for prompt injection, jailbreaks, guardrail bypasses, adversarial behavior, and other attack vectors.
• Identify vulnerabilities involving data leakage, privacy exposure, authentication, authorization, and access controls.
• Assess AI agents, APIs, and enterprise integrations for unintended or unauthorized actions.
• Perform hallucination, adversarial robustness, and AI-specific security testing across enterprise AI solutions.
• Develop and automate repeatable AI security testing methodologies and workflows.
• Document vulnerabilities clearly, assess their potential impact, and support remediation efforts.
• Apply established AI security frameworks and best practices to strengthen the resilience of AI-enabled systems.

Requirements:

• 4-10+ years of relevant professional experience in cybersecurity, application security, penetration testing, AI security, or a closely related discipline.
• Strong hands-on knowledge of LLM and Generative AI security, including AI red teaming and adversarial testing.
• Experience assessing prompt injection, jailbreaks, RAG architectures, agentic AI systems, and AI guardrails.
• Solid understanding of API security, penetration testing, cloud security, privacy, and access-control vulnerabilities.
• Practical programming and automation skills, particularly with Python.
• Familiarity with security frameworks and standards such as the OWASP LLM Top 10 and MITRE ATLAS.
• Ability to investigate complex AI security issues, think adversarially, and translate technical findings into clear remediation recommendations.
• Strong analytical, problem-solving, documentation, and communication skills.
• Comfortable working independently across complex technical environments and adapting to rapidly evolving AI security threats.

Benefits:

• Fully remote opportunity open to candidates based in India, with global collaboration.
• Opportunity to work on cutting-edge AI security challenges across enterprise environments.
• Exposure to LLMs, RAG systems, AI agents, cloud platforms, APIs, and emerging AI security technologies.
• Opportunity to contribute to the security of AI solutions used across banking, finance, audit, semiconductor, and technology sectors.
• Hands-on experience with AI red teaming, adversarial testing, vulnerability research, and security automation.
• Opportunity to help shape stronger security practices for rapidly evolving enterprise AI systems.
• Global, technology-focused environment with opportunities to apply and expand advanced cybersecurity expertise.