Back
Remote hiring and mid-level experience increase candidate density, though role's niche AI-security skills limit applicants.
Highly specialized AI-red-team and LLM security skills limit cross-industry transferability.
Explicit 4–10 years requirement and mandatory LLM security skills enforce strict filtering.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Conduct red-teaming and adversarial testing of LLMs, RAG systems, and AI agents to uncover vulnerabilities such as prompt injections, jailbreaks, and guardrail bypasses.
Identify security issues including data leakage, privacy breaches, access-control flaws, unauthorized AI actions, hallucinations, and other AI-specific threats in enterprise AI solutions.
Automate AI security testing processes and manage documentation and remediation of identified vulnerabilities.
Experience Required: 4 to 10+ years in relevant AI security, red teaming or penetration testing roles.
Domain Expertise: Experience with LLM/Generative AI security and red teaming of AI systems is mandatory.
Technical Skills: Proficiency in Python, AI security concepts (e.g., OWASP LLM Top 10, MITRE ATLAS), API security, cloud security, and penetration testing techniques.
Location: India or Global (Fully remote opportunity).
Experienced in security testing of AI enterprise systems within banking, finance, audit, semiconductor, or technology industries.
Comfortable working with advanced AI constructs such as prompt injections, jailbreaks, RAG systems, and agentic AI.
Capable of both manual and automated AI security testing with strong documentation and vulnerability remediation skills.