Jobs

Mirendil is seeking a Member of Technical Staff for their Post-Training, RL Infra team to build the post-training stack for frontier reasoning models. This role is at the intersection of research and infrastructure, focusing on scaling their RL stack through novel ideas, reliability, and performance. Responsibilities include designing large-scale RL training infrastructure, implementing performance optimizations, developing evaluation tools, and building data collection pipelines. The ideal candidate is excited about enabling frontier RL research at scale.