Senior Penetration Tester (AI Security / Purple Team)

O projekcie This role combines hands-on AI security testing, adversary simulation, and Purple Team activities. You will focus on identifying security weaknesses in emerging technologies, particularly AI-powered solutions, and evaluating how effectively existing security controls can prevent, detect, and respond to realistic cyber threats.

About the opportunity

You will have the opportunity to work on complex security challenges in a large-scale enterprise environment, with a particular focus on emerging AI technologies.

The position offers a combination of hands-on offensive security research, realistic attack simulations, and collaboration with cybersecurity teams responsible for protecting critical systems and service

Zakres obowiązków

• Your responsibilities
• Conduct offensive security assessments of AI-powered applications, including LLMs, GenAI solutions, RAG systems, AI agents, and MCP-based integrations.
• Identify and test AI-specific vulnerabilities such as prompt injection, sensitive data exposure, insecure tool execution, and weaknesses in agent permissions and workflows.
• Design and execute adversary simulation scenarios based on real-world attack techniques and threat intelligence.
• Evaluate the effectiveness of security controls across enterprise infrastructure, cloud platforms, endpoints, and AI environments.
• Develop and customize scripts, testing tools, and attack scenarios to support security assessments.
• Work closely with Red Team, Blue Team, SOC, and Detection Engineering teams to improve threat detection and response capabilities.
• Document findings, assess security risks, and provide actionable recommendations to technical and business stakeholders.
• Research emerging attack techniques and contribute to the continuous improvement of offensive security practices.

Wymagania What we're looking for

• Hands-on experience in AI/LLM security testing is essential, including offensive assessments of GenAI applications, AI agents, or other AI-powered enterprise solutions.
• At least 3 years of experience in Red Teaming or Purple Teaming, or 4+ years in offensive security, including relevant hands-on testing in complex technology environments.
• Practical knowledge of AI security threats, including prompt injection, RAG-related vulnerabilities, insecure tool usage, and attacks targeting AI agents.
• Understanding of LLM architectures, AI application integrations, APIs, RAG pipelines, and agent-based systems.
• Experience with adversary simulation, attack techniques, and threat-informed security testing.
• Strong scripting or programming skills in Python, PowerShell, Bash, C/C++, or C#.
• Familiarity with offensive security tools and frameworks used in advanced security assessments.
• Ability to independently plan and execute technical security assessments and communicate findings clearly.
• Good communication skills and experience working with cross-functional technical teams.

Nice to have

• Experience with AWS or Azure security testing.
• Knowledge of cloud identity and access management, including RBAC, managed identities, and service principals.
• Experience with Cobalt Strike, Brute Ratel, or similar adversary simulation frameworks.
• Certifications such as OSCP, OSEP, OSED, CRTO, OSAI, or equivalent.