Artificial Intelligence Security Specialist

Job Title : AI Red Team Engineer

This is a high-priority role for an experienced offensive security engineer to lead the testing of artificial intelligence (AI) agents, including language models (LLMs) that access sensitive data. The goal is to identify vulnerabilities, prompt-injection pathways, and data-exfiltration risks before they can be exploited by malicious actors.

• 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.
• Verify policy compliance (e.g., PD5, FA2) and attempt policy bypasses.
• Write clear vulnerability reports (CVE, bug bounty).

Requirements include 2+ years of experience in offensive security or adversarial ML, proficiency in AppSec techniques (XSS, CSRF, SSRF), LLM issues, and experience with browser automation, terminal commands, and API attacks. Scripting skills in Python / bash inside VMs are also required. Additionally, a strong track record in vulnerability reporting (CVE, HackerOne) and knowledge of privacy & financial-risk policies (GDPR, SOC2) are essential.

We offer a competitive salary and benefits package, including medical, dental, and vision insurance, 401(k) matching, and generous paid time off. Our team is passionate about AI security and committed to innovation and excellence.

Please note that this is a highly competitive role, and we will only consider candidates with the most relevant experience and skills.