Your goal is to conduct cutting-edge research into novel attack vectors and vulnerabilities, using those insights to both sharpen our AI and lead the industry conversation on AI-driven security. Youll work alongside a tight-knit team building excellent software in the security space.
Responsibilites
Original Research: Develop new attack strategies and offensive testing techniques for web, network and AI targets, and translate real-world knowledge into improvements for the AI agent
Thought Leadership: Produce high-quality technical content, including research papers, stage demonstrations, or technical blog posts that showcase unique capabilities and security philosophy.
Public Advocacy: Represent research at major security conferences and industry events.
AI Enhancement: Part of the team improving the AI hacker to make it more dangerous and creative.
Collaboration: Work closely with AI and engineering teams to continuously improve agent capabilities and ensure research findings are integrated into the product.
Technical Expertise: Deep expertise in Web and API security, including authentication, business logic, and injection flaws.
Publication Record: Proven experience publishing technical security research (e.g., personal or company blogs, whitepapers) or presenting at recognized security conferences (e.g., Black Hat, DEF CON, OWASP).
Coding Proficiency: Experience in writing code to develop tooling for penetration tests and security research.
Startup Mindset: Comfortable working in a fast-paced environment with a high degree of ownership and curiosity.
