AI Red Team Security Lead

• UoP only
• Warsaw - hybrid work
  

We are looking for our Client an experienced AI Security Red Team Leadto lead offensive security testing of AI systems and strengthen the organization's AI security capabilities. This role combines hands-on red teaming, vulnerability research, and collaboration with senior stakeholders to identify and mitigate emerging AI-related risks.

Key responsibilities:

• Lead and execute AI Red Team engagements and security assessments.
• Identify, test, and analyze vulnerabilities in AI systems and applications.
• Assess AI-specific threats and attack techniques.
• Develop custom tools and automation to support offensive security activities.
• Advise technical and business stakeholders on AI security risks and mitigations.
• Act as an SME in Offensive AI Security and stay current with the latest trends and threats.

Key requirements:

• 5+ years of experience in Red Teaming, Penetration Testing, Vulnerability Research, or Exploit Development.
• Experience with structured red team exercises such as TIBER-EU, CBEST, or similar.
• 3+ years of web exploitation experience and at least 1 year of AI Red Teaming experience.
• Strong understanding of AI threats, attack techniques, frameworks, and technology stacks.
• Experience in AI vulnerability analysis.
• Strong coding and scripting skills for building security tools and automation.
• Excellent English and stakeholder communication skills.

Nice to have:

• Advanced offensive security certifications (OSCP+, OSEE, OSCE3, SEC542, SEC522).
• AI Red Team certifications.
• CVEs, security research publications, or conference presentations.
• Contributions to open-source or commercial security tools.

What you need to do now

If you're interested in this role, click 'apply now' to forward an up-to-date copy of your CV, or call us now.

Hays Poland sp. z o.o. is an employment agency registered in a registry kept by Marshal of the Mazowieckie Voivodeship under the number 361.