Find real-world vulnerabilities, build exploit chains and patches, and test whether AI models block or enable attacks. Suits offensive security and red team professionals with OSCP-level skills.
Sobre la vacante
Sepal AI is hiring contributors to a vulnerability and exploit benchmark to make sure next-generation AI can’t be hijacked or exploited in enterprise environments. We need OSCP-certified, red-teamers, and CTF veterans to identify vulnerabilities and generate exploits.
🧠 What You'll Do
- Identify real-world vulnerabilities.
- Generate exploits to crash provided systems.
- Generating patches to remediate & test the vulnerability
- Craft realistic exploit chains and payloads a real attacker might use, then measure whether the model blocks or facilitates the attack.
✅ Who You Are
- OSCP (or comparable) certification and 3+ years in professional red teaming or offensive security.
- Proven CTF track record; comfortable with web, cloud, and application exploits.
- Fluent in Python/Bash/Docker tooling, custom payload development, and exploit automation.
- Strong grasp of common enterprise stacks (OAuth, SAML, REST, SQL, cloud IAM).
- Passionate about AI safety and eager to keep cutting-edge models from becoming attack surfaces.
💸 Pay: $40–90/hr
🌍 Remote
⏱ Flexible hours (project-based, async)
Education: Bachelor's degree completed
Fuente oficial: expert-hub.sepalai.com. Los detalles pueden cambiar; la página de la plataforma tiene la última palabra.¿Hay algún error en esta oferta? Avísanos.
Más trabajos de red teaming y seguridad Todas las vacantes de Sepal AI ¿Cuánto paga Sepal AI?
