Cybersecurity Expert - AI Agent Threat Detection

Job Title : Artificial Intelligence Defender

Role Overview :

A highly skilled Artificial Intelligence Defender is needed to lead offensive security testing of AI agents, including Large Language Models (LLMs) that can access connectors.

Responsibilities :

• Design and automate multi-turn attacks involving browser, terminal, and API misuse.
• Create prompt-injection and data-exfiltration attack scenarios.
• Script repeatable tests in Python or bash inside Virtual Machines (VMs).
• Verify policy compliance and attempt policy bypasses.
• Write clear vulnerability reports.

Requirements :

Duration : 2 Months Contract

Location : Remote

The ideal candidate will design and automate multi-turn attacks, create prompt-injection and data-exfiltration attack scenarios, script repeatable tests, verify policy compliance, and write clear vulnerability reports. Strong knowledge of AppSec techniques, browser automation, terminal commands, API attacks, and Python / bash scripting is required. A proven track record in vulnerability reporting and knowledge of privacy and financial-risk policies are also necessary.