At a Glance
- Tasks: Identify vulnerabilities in AI systems through adversarial testing and design challenging prompts.
- Company: Obsidian, a leader in AI safety and innovation.
- Benefits: Competitive salary, flexible work options, and opportunities for professional growth.
- Other info: Join a dynamic team dedicated to improving AI alignment and robustness.
- Why this job: Make a real impact on AI safety and contribute to cutting-edge research.
- Qualifications: Experience in AI safety and strong analytical skills.
The predicted salary is between 63000 - 77000 £ per year.
Obsidian seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.
You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics.
You will document findings, contribute to safety benchmarking and red-teaming reports, and collaborate with AI researchers to improve alignment, robustness, and safety in real-world deployments.
#J-18808-Ljbffr
AI Safety Red Team Expert – Frontier Model Testing employer: Obsidian
At Obsidian, we pride ourselves on fostering a collaborative and innovative work culture that empowers our ML Scientists to push the boundaries of machine learning research. Located in a vibrant tech hub, we offer competitive compensation, flexible project-based work, and ample opportunities for professional growth, making us an excellent employer for those looking to make a meaningful impact in the field of AI.
