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-Ljbffr
Full job description from WhatJobs. Apply for this role →
London
AI systems are only as safe as the people who test them — and that's where you come in.
Explore: Specialist jobs in London
Worked with Verifera as a candidate or employer? Your honest review helps the next person trust verified hiring.