Zealogics.com·USA·18 авг.
Experience: 4–10+ Years Location: India / Global Zealogics is looking for an AI Red Team Engineer to identify vulnerabilities and strengthen enterprise AI solutions used across banking, finance, audit, semiconductor, and technology industries. Key Responsibilities Red-team LLMs, RAG systems and AI agents. Test prompt injection, jailbreaks and guardrail bypasses. Identify data leakage, privacy and access-control vulnerabilities. Test AI agents, APIs and enterprise integrations for unauthorized actions. Perform adversarial, hallucination and AI security testing. Automate AI security testing and document/remediate vulnerabilities. Key Skills: LLM/GenAI Security, AI Red Teaming, Prompt Injection, RAG, Agentic AI, API Security, Penetration Testing, Python, OWASP LLM Top 10, MITRE ATLAS, Cloud Security.