Member of Technical Staff - Post-Training

Reflection is on a mission to build open superintelligence and make it accessible to all. They are seeking a Member of Technical Staff to build systems that transform pre-trained models into aligned agents and drive research initiatives in post-training optimization. Responsibilities Build systems that transform powerful pre-trained models into aligned and general agentsDrive research and engineering initiatives that push the frontier of post-training, from data curation to large-scale optimizationDevelop data generation pipelines, reward models, reinforcement learning algorithms, and inference-time scaling techniquesCollaborate across pre-training and post-training teams to deliver step-function gains in model capabilityContribute to shaping our understanding of how large models learn to reason, follow instructions, and improve through reinforcement learning