Apollo Research
Rusheb Shah has a strong background in software engineering, specializing in designing and implementing high-scale and fault-tolerant systems. Currently working as a Research Engineer at Apollo Research, they previously held roles at companies such as OpenAI, Amazon Web Services, R3, and Brainlabs. With a Master's Degree in Materials Science from the University of Oxford and additional education from Alignment Research Engineer Accelerator (ARENA) and Hampton School, Rusheb Shah has valuable experience in building and testing engineering functions for various platforms.
This person is not in any offices
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.