AI Red Team Engineer / AI Security Specialist

📋 Description

• Conduct red-team assessments of LLMs, RAG systems, AI agents, and gen AI apps.
• Test for prompt injection, jailbreaks, guardrail bypasses, adversarial behavior.
• Identify data leakage, privacy, auth, and access-control vulnerabilities.
• Assess AI agents, APIs, and enterprise integrations for unauthorized actions.
• Perform AI-specific security testing across enterprise AI solutions.
• Develop repeatable AI security testing methodologies and automation.

🎯 Requirements

• 4–10+ years in cybersecurity, app security, pen testing, or AI security.
• Hands-on knowledge of LLM security, red teaming, and adversarial testing.
• Experience with prompt injection, jailbreaks, RAG, agentic AI, and guardrails.
• Strong API security, cloud security, privacy, and access-control skills.
• Programming/automation skills, especially Python.
• Familiarity with OWASP LLM Top 10 and MITRE ATLAS.

🎁 Benefits

• Fully remote opportunity; candidates in India welcome.
• Work on cutting-edge AI security challenges across enterprises.
• Exposure to LLMs, RAG, AI agents, cloud platforms, and APIs.
• Opportunity to impact security of AI solutions in finance, banking, tech sectors.
• Hands-on AI red teaming, vulnerability research, and security automation.
• Shape stronger security practices for evolving enterprise AI systems.