AI Red Team Engineer

THE OPPORTUNITY

We are currently building Watcher,  a monitoring tool for coding agents. Our monitoring research agenda attempts to translate compute into safety at scale. Red-teaming previously sat inside the RS (Control) role as a partial responsibility. As it's grown from a single pilot into a recurring need, it now needs a dedicated owner.

As the AI Red Team Engineer, you will help build the practice of red-teaming AI monitors (both Watcher's own defenses and frontier labs' monitoring systems (see our pilot campaign red-teaming Anthropic's auto mode). You will hunt for attack surfaces monitors that haven't been tested against yet and turn what you find into fixes. You'll work closely with Marius (CEO & currently leads the monitoring efforts), control researchers and product engineers. 

You will like this opportunity if you think like an attacker and want your adversarial findings to directly strengthen AI monitoring systems. You will join a small team and will have significant ability to shape the team & tech, and have the ability to earn responsibility quickly. 

• 1. Downplaying existential risks or safety concerns associated with advanced AI deployment
• 2. Lack of deep technical familiarity with neural network internals or transformer architectures
• 3. Prioritizing speed of deployment over thorough, scientifically sound safety testing

I advance frontier AI safety by combining rigorous mechanistic interpretability with empirical evaluations of complex neural systems.