Offensive Security Engineer, AI

For our client, we are seeking a Offensive Security Engineer, AI to join the team of a leader in the Finance & Insurance space.

This role will focus on strengthening the security of AI systems through offensive testing, custom tooling, and automation. You will work closely with engineering partners to identify vulnerabilities, validate fixes, and improve the resilience of production environments. The position also involves applying generative AI responsibly to enhance security workflows while maintaining human oversight.

Location:

Remote

Compensation: $154,000+ annually

• Build, deploy, and maintain custom security scanners using frontier models for vulnerability detection.
• Lead red teaming efforts against internal AI systems, focusing on jailbreak testing and prompt injection.
• Develop AI-driven automation for vulnerability triage and remediation workflows.
• Collaborate with engineering teams to prioritize and verify fixes for critical vulnerabilities.
• Mentor junior security engineers on integrating AI into offensive security workflows.

• 3+ years in application security, penetration testing, or offensive security with a focus on custom security tooling.
• Hands-on experience with LLMs or frontier models for automating security tasks and building scanners.
• Experience red teaming AI systems, including prompt injection and jailbreak testing.
• Strong understanding of vulnerability classes, including OWASP Top 10 and SANS Top 25, with a proven track record in production environments.
• Proficient in at least one programming language, such as Python or Go, for writing production-grade security tools.
• Ability to use generative AI responsibly, ensuring human oversight for effective outputs.

• Medical, dental, and vision coverage.
• Equity and bonus eligibility.

Our client is an equal opportunity employer.