DescriptionAbout the roleThis is a rare opportunity to work at the intersection of offensive security and AI - and to have your expertise shape a platform used at enterprise scale. You'll perform attacks on customer applications, help the AI agent get smarter, and work alongside a tight-knit team building something genuinely new in the security space. Work closely with AI and engineering teams to continuously improve agent capabilities.
Responsibilites- Harness Tenzai's AI agent on customer applications, analyze the results, and validate vulnerabilities with clear exploitation evidence.
- Present findings and exploitation evidence clearly and transparently to customers and internal teams
- Analyze where the system needs to improve, investigate cases where the AI missed, misclassified, or hallucinated vulnerabilities.
- Develop new attack strategies and offensive testing techniques for web and API targets, and translate real-world knowledge into improvements for the AI agent.
Requirements- Deep expertise in Web and API security, including authentication, business logic, and injection flaws
- 3+ years of hands-on experience in Penetration Testing, Application Security, Bug Bounty, or Red Team operations
- Ability to articulate complex vulnerabilities clearly, both in writing and verbally.
- Experience in writing code to develop tooling for penetration tests
- Comfortable working in a fast-paced startup environment with a high degree of ownership
