Job description
Andon Labs • San Francisco Bay Area
San Francisco Bay Area
$100,000 - $180,000
- In this role, you'll design and run evaluations probing AI behavior in real-world deployments to ensure safety and alignment.
- Determine what to measure and how to capture AI safety across deployed autonomous organisations.
- Interpret evaluation results and identify patterns in AI behavior that indicate misalignment.
- Implement control protocols to keep Safe Autonomous Organisations secure and aligned.
- Execute experiments with research intuition to uncover novel safety insights.
Andon Labs prepares for a future where organizations are run autonomously by AI by benchmarking and deploying frontier AI in the real world.