Agentic AI Security Engineer

Job Summary

We are looking for an Agentic AI Security Engineer to secure AI-powered autonomous agents, multi-agent systems, and LLM-based applications. The candidate will focus on identifying AI-specific security risks, implementing guardrails, protecting AI workflows, and ensuring secure agent-to-tool interactions.

Key Responsibilities

• Design and implement security controls for autonomous AI agents.
• Secure LLM-based applications and multi-agent architectures.
• Implement guardrails against prompt injection, jailbreaks, and data leakage.
• Secure agent-to-tool integrations and API communication.
• Implement authentication, authorization, and access control for AI agents.
• Conduct AI red teaming and adversarial security testing.
• Protect AI systems against model manipulation and unauthorized actions.
• Monitor agent behavior and detect anomalous activities.
• Implement secure memory management and data access policies.
• Develop security frameworks for agentic AI deployments.

Required Skills

• Experience in AI security, application security, or cloud security.
• Strong understanding of LLMs, generative AI, and AI agent architectures.
• Experience with Python and REST API integrations.
• Knowledge of LangChain, LangGraph, AutoGen, or similar agent frameworks.
• Understanding of prompt injection, jailbreaks, and AI threat modeling.
• Knowledge of OWASP Top 10 for LLM Applications.
• Experience with identity management and secure API integrations.

Familiarity with AI security testing and guardrail implementations