Frontier AI Safety Red Teamer
Role Description & Technical Scope
Obsidian is seeking experienced AI Safety Red Teamers in the United Kingdom to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate behavior across high-risk topics.
Responsibilities include designing jailbreak tests, documenting findings, and collaborating with researchers to improve alignment, robustness, and safety of AI systems. A strong background in AI safety and red-teaming is essential.
#J-18808-LjbffrReady to apply for this cyber security position?
This opportunity is hosted on CV-Library. Click below to view full details and submit your application.
Key Details
- Date Posted: 19 Oct 2026
- Location: london
- Employment: Permanent
- Workplace: Hybrid
- Domain: IT & Technology, Other
Need an ATS CV for this role?
Optimize your cyber CV with ATS-friendly templates before submitting your application.
Build Free CV NowEmployer Profile
Obsidian
Verified Tech EmployerEnterprise technology firm or security consultancy operating across the UK digital defense ecosystem.
More Jobs at Obsidian