Náplň práce
Join an international organization at the forefront of AI security, where your expertise will help uncover and address vulnerabilities in modern AI systems.
The role gives you hands-on exposure to AI Red Teaming, MITRE ATLAS, OWASP Top 10 for LLM Applications, PyRIT, Garak, HexStrike, Giskard, DeepTeam, vulnerability research, Python, and offensive security automation.
- Conduct offensive security assessments and AI Red Team exercises against AI systems, models, applications, and supporting infrastructure
- Identify vulnerabilities, attack paths, security weaknesses, and misconfigurations across complex AI environments
- Evaluate AI security products and solutions through hands-on offensive testing
- Develop and improve Red Team tools, automation, and TTPs using technologies such as PyRIT, Garak, HexStrike, Giskard, and DeepTeam
- Perform detailed vulnerability and risk assessments, including impact, exploitability, complexity, and remediation priorities
- Document technical findings and present clear recommendations to security teams, senior stakeholders, and technical experts
- Continuously research emerging AI threats and strengthen offensive security capabilities and testing methodologies
Požadavky
- 5+ years of professional experience in offensive security, including Red Teaming, penetration testing, vulnerability research, or exploit development
- 3+ years of experience with web exploitation within offensive security activities
- 1+ year of hands-on experience in AI Red Teaming
- Experience with structured security exercises such as TIBER-EU, CBEST, or similar frameworks is an advantage
- Strong understanding of AI security threats and TTPs, including MITRE ATLAS and OWASP Top 10 for LLM Applications
- Excellent coding and scripting skills, with the ability to develop custom security tools and automation
- Proven experience analyzing AI vulnerabilities and strong understanding of AI technologies, frameworks, and security concepts
- Fluent English with excellent communication and presentation skills
Nice to Have
- CVEs, vulnerability disclosures, security research, or publications at recognized security conferences
- Advanced offensive security certifications such as OSCP+, OSEE, OSCE3, SEC542, or SEC522
- AI Red Team certifications such as AIRTP+, CAIRTP, CAIPT-RT, or C-AI/MLPen
- Contributions to open-source or commercial offensive security and AI security tools
- Bachelor's or Master's degree in Computer Science, Information Technology, or a related field
Odpovědět na inzerát