About the job
About Anthropic
At Anthropic, we are driven by our mission to develop reliable, interpretable, and steerable AI systems. Our commitment is to ensure that AI is safe and beneficial not only for our users but also for society as a whole. Our rapidly expanding team comprises dedicated researchers, engineers, policy specialists, and business leaders collaborating to create impactful AI technologies.
About the Role:
- Scalable Oversight: Innovating techniques to ensure that highly capable models remain helpful and truthful, even as they exceed human-level intelligence.
- AI Control: Developing strategies to maintain the safety and harmlessness of advanced AI systems in novel or adversarial environments.
- Alignment Stress Testing: Implementing rigorous testing frameworks to evaluate AI alignment under various conditions.

