Member of Technical Staff - Research Scientist

Own and drive foundational research defining how agentic AI systems are trained, evaluated, and improved. Work at the intersection of reinforcement learning, simulations, and scalable oversight to build agent simulation, evaluation, and RL environments used to stress-test frontier models. Lead end-to-end research projects on reward design, environment design, curriculum learning, and trajectory evaluation, publish and share artifacts, and integrate production-level research code with cross-functional teams.