About the company:
We have partnered with a renowned global leader in information and communications technology (ICT) infrastructure and smart devices.
They are providing full-stack, all-scenario solution for products and services carriers, enterprises, governments, and individual consumers worldwide.
Our client is looking for a seasoned
AI Agent Security Engineer
to join their AIOS Security R&D team to design and implement advanced security mechanisms that protect mobile, PC, and IoT environments from emerging risks associated with AI agents, large language models (LLMs), and high-privilege systems.
This role focuses on system-level protection, kernel security, AI agent security, and access control frameworks to prevent exploitation and ensure system integrity.
Key Responsibilities:
Design and implement robust security mechanisms for AI-driven systems across mobile, PC, and IoT platforms.
Address AI/LLM security risks, including prompt injection, adversarial ML exploitation, and over-privileged AI agent behaviors.
Develop and enhance access control frameworks for AI Agent interactions and kernel security.
Work with technologies like SELinux, AppArmor, and other Mandatory Access Control (MAC) systems.
Secure API gateways and system communications involving AI agents.
Contribute to kernel hardening initiatives, such as memory protection and syscall filtering, to ensure system resilience.
Qualifications:
Master’s or PhD in Computer Science, Cybersecurity, or AI/AI Agent Security.
Proven industry experience in OS security, particularly in mobile (Android/iOS) or Linux kernel security.
Proficiency in C/C++ for system-level programming (kernel modules, OS security).
Strong understanding of OS security mechanisms, including Mandatory Access Control (MAC) frameworks like SELinux and AppArmor, as well as kernel hardening techniques such as memory protection and syscall filtering.
Experience in AI/LLM security, including prompt injection attacks, adversarial ML exploits, and the risks of over-privileged AI agents.
Familiarity with mobile and PC security frameworks (e.g., Android SE, iOS Sandbox, Linux security modules).
Prior work experience with AI Agents or Large Language Models (LLMs).
Contributions to system security projects (e.g., Linux kernel, Android AOSP).
We are an equal opportunities employer and welcome applications from all qualified candidates.
#J-18808-Ljbffr