AI Security Engineer: Defending LLMs & Autonomous Agents

Systems Limited; Islamabad; On-site; PKR 1,800,000 - 3,200,000; Full time

Job summary

Systems Limited is seeking an experienced AI security specialist to design and implement security controls for AI systems, LLMs, and autonomous agents. You will threat-model AI architectures, defend against prompt injection and tool abuse, and establish robust identity and access controls.

The role requires hands-on testing, red-team activities, privacy reviews, and collaboration with Governance and Platform Engineering to lift the organization’s security posture.

Qualifications

• 5+ years of cybersecurity/AppSec experience, including 2+ years in AI/LLM/Agent Security.

Responsibilities

• Design AI security architecture and threat modeling for AI systems, LLMs, and autonomous agents.
• Implement defenses against prompt injection, jailbreaks, and tool abuse by agents.
• Define AI identity, authentication, authorization, and access controls.
• Conduct AI security testing, adversarial testing, and red-team exercises.
• Perform AI privacy reviews covering PII, prompts, outputs, and logs.
• Partner with AI Governance and Platform Engineering to strengthen security posture.
• Communicate AI-specific risks and vulnerabilities to security leadership.
• Identify and remediate vulnerabilities and emerging AI threats.
• Train delivery teams on AI security best practices and threat patterns.

Skills

AI/LLM security

Threat modeling

IAM & network security

Adversarial testing

Security communication

Education

Bachelor's degree in CS or related

Tools

NeMo Guardrails

Rebuff

Azure AI Foundry Prompt Shields

AWS Bedrock Guardrails

Vertex AI safety controls

Job description

Systems Limited is seeking an experienced AI security specialist to design and implement security controls for AI systems, LLMs, and autonomous agents. You will threat-model AI architectures, defend against prompt injection and tool abuse, and establish robust identity and access controls.

The role requires hands-on testing, red-team activities, privacy reviews, and collaboration with Governance and Platform Engineering to lift the organization’s security posture.