This is a hands-on role for a seasoned offensive researcher who thrives on technical depth and creativity. Youll collaborate closely with product, marketing, and engineering teams to deliver research that drives customer trust, informs product direction, and shapes industry thought leadership.
What Youll Do
Perform AI-Focused Vulnerability Research: Investigate security risks in AI models, APIs, and infrastructure to uncover exploitable weaknesses and publish insights that strengthen our market leadership.
Lead Red Teaming Against AI Systems: Simulate adversarial attacks on AI pipelines and APIs, creating impactful PoCs that showcase real-world risk and defensive strategies.
Build Customer-Facing Proof-of-Concepts: Partner with product and engineering teams to design and deliver PoCs that align with customer use cases and highlight security capabilities.
5+ years in Security Research or Offensive Engineering with a proven track record in penetration testing or vulnerability discovery on complex targets.
Deep expertise in Application & AI Security, including experience exploiting APIs, web applications, and AI/ML vulnerabilities such as prompt injection, adversarial manipulation, or model abuse.
Offensive Security & Red Teaming Experience, with practical use of tools, custom exploits, or adversarial testing methods.
Proficiency in developing and presenting PoCs that clearly demonstrate security risks to both technical and non-technical audiences.
Recognized achievements in Bug Bounty or Military-Grade Security Research, or equivalent real-world offensive security experience.
Solid software engineering background, with the ability to read, write, and debug code (Python, JavaScript, Go, etc.).
