Apollo Research
Full-time · London, United Kingdom
Beyond our active and open positions, we will likely hire for the broad roles listed below in the future.
If you have an interest in these future roles please feel free to submit your CV and info. here under Expression of Interest. If you have an interest in working at Apollo Research and your skills and work interests are outside of the above listings, please also apply here under Expression of Interest. Please tell us more about your background and the type of role you see yourself within Apollo. We're interested in hiring people from diverse and non-traditional backgrounds.
This job is not in any teams
Apollo Research
Apollo Research is an AI safety organization. We specialize in auditing high-risk failure modes, particularly deceptive alignment, in large AI models. Our primary objective is to minimize catastrophic risks associated with advanced AI systems that may exhibit deceptive behavior, where misaligned models appear aligned in order to pursue their own objectives. Our approach involves conducting fundamental research on interpretability and behavioral model evaluations, which we then use to audit real-world models. Ultimately, our goal is to leverage interpretability tools for model evaluations, as we believe that examining model internals in combination with behavioral evaluations offers stronger safety assurances compared to behavioral evaluations alone.