
Apollo Research is an AI safety organization specializing in auditing high-risk failure modes, particularly deceptive alignment, in large AI models. We conduct fundamental research on interpretability and behavioral model evaluations to minimize catastrophic risks associated with advanced AI systems. Our distinctive approach combines examining model internals with behavioral evaluations to provide stronger safety assurances.
Apollo Research is seeking to build its team and invites interested candidates to submit their CV and information under Expression of Interest. They are looking for individuals interested in roles such as Evals Research Engineers/Scientists, Research Leads, Full-stack Software Engineers, Operations Generalists/Specialists, and Governance Experts (UK, USA, EU). Applicants with skills outside of these listed roles are also encouraged to apply.
Apollo Research is an AI safety organization specializing in auditing high-risk failure modes, particularly deceptive alignment, in large AI models. We conduct fundamental research on interpretability and behavioral model evaluations to minimize catastrophic risks associated with advanced AI systems. Our distinctive approach combines examining model internals with behavioral evaluations to provide stronger safety assurances.
Apollo Research