AI Security Red Team Engineer
Confirmed on the employer's own hiring board on Oct 19, 2026. First seen by Alion on Sep 21, 2026.
Description:
Want to challenge the security of next-generation AI systems?
We are looking for a Senior AI Security Engineer specializing in Red Teaming to help identify and mitigate security risks in next-generation AI systems within an international environment.
This role combines offensive security expertise, AI security research, and hands-on technical assessments. You will work on AI red team engagements, vulnerability analysis, and the development of new testing approaches for emerging AI technologies.
Your Responsibilities:
- Lead and execute AI red team engagements targeting AI applications, models, and supporting infrastructure
- Identify vulnerabilities, attack paths, and security weaknesses through offensive testing
- Evaluate AI security solutions and assess their effectiveness
- Develop and improve AI red teaming tools, methodologies, and testing techniques (e.g. PyRIT, Garak, Giskard, DeepTeam).
- Research emerging AI threats, attack techniques, and security trends
- Prepare risk assessments and technical reports including impact, exploitability, prioritization, and remediation recommendations
- Act as a subject matter expert (SME) in Offensive AI Security, advising senior technical and business stakeholders
Requirements:
Your Profile:
- 5+ years of experience in offensive security, with experience in red teaming, penetration testing, vulnerability research, or exploit development
- At least 3 years of experience with web application exploitation and offensive security methodologies
- At least 1 year of hands-on experience with AI red teaming
- Deep understanding of AI technologies, model architectures, technology stacks, and AI security frameworks such as MITRE ATLAS and OWASP Top 10 for LLM Applications
- Strong programming and scripting skills with the ability to develop custom security tools
- Experience identifying and analyzing vulnerabilities in AI-based systems
- Excellent communication skills and English at B2/C1 level for daily professional communication within an international team
Nice to Have:
- Advanced offensive security certifications such as OSCP, OSEE, OSCE3, SEC542, or SEC522
- AI security certifications such as AIRTP+, CAIRTP, CAIPT-RT, or C-AI/MLPen
- Contributions to open-source or commercial offensive security tools, preferably AI security tools
- Publications at recognized security conferences (e.g. Black Hat, DEF CON, Chaos Communication Congress) or vulnerability disclosures (CVEs)
- Degree in Computer Science, Cybersecurity, Information Technology, or related field
Other information:
Benefits:
What We Offer?
- Annual bonus of up to 20% of gross annual salary
- Flexible working hours and hybrid work model (3-4 days of home office per week)
- Company car for private use or car allowance of 10 800 CZK/month
- 5 weeks of vacation + 6 sick days and additional days off for long-term cooperation
- Multisport card, Edenred benefits, and meal allowance
- Pension and life insurance contributions
- Professional development, training, and certifications
- Employee share purchase program
- Company events and wellbeing activities
Send us your CV in English and Czech if you have one. For more related job opportunities visit https://www.grafton.cz/en/job-search
Please, quote the reference number 1005305