We are looking for a
Senior Penetration Tester (Red Team – AI Security)
with a strong hands-on offensive security background and practical exposure to
AI Security
.
This role focuses on security testing of
LLMs, chatbots, AI agents and Generative AI applications
, combined with traditional
Web Application and API Penetration Testing
.
We are specifically looking for someone whose primary function is Red Team / Offensive Security.
We are not looking for a cybersecurity generalist whose experience is mainly focused on SOC, GRC, Vulnerability Management, Security Architecture or Security Operations.
What You'll Do
- Perform hands-on
Red Team and Penetration Testing
activities.
- Test
LLMs, chatbots, AI agents, web applications and APIs
.
- Design and execute attack scenarios involving:
- Prompt Injection / Indirect Prompt Injection
- Jailbreaks
- Sensitive Information Disclosure
- Instruction Manipulation
- Agent / Tool Abuse
- Data & Model Poisoning
- Identify vulnerabilities based on the
OWASP Top 10 for LLM Applications
.
- Assess authentication, authorization,
sessions, business logic and information exposure.
- Develop Proofs of Concept and reproduce real attack scenarios.
- Automate security testing using
Python, Bash, PowerShell or similar technologies
.
- Document findings, evidence, impact, risk and remediation recommendations.
- Present technical results and collaborate with international teams.
What We're Looking For
- 6+ years of hands-on Penetration Testing / Offensive Security experience.
- 3+ years of hands-on Red Team experience.
- Red Team / Offensive Security must be a primary area of responsibility in current or recent professional experience.
- Strong experience performing
Web Application and API Penetration Testing
.
- Experience designing and executing attack scenarios, not only vulnerability scanning or vulnerability management.
- Practical knowledge or hands-on exposure to
LLMs, Chatbots, AI Agents and Generative AI applications
.
- Knowledg