Senior Software Engineer, RL Post-Training Frameworks
This role involves designing and building scalable reinforcement learning (RL) post-training infrastructure that supports the full lifecycle of training, inference, and rollout across heterogeneous hardware. The engineer will contribute to open-source RL frameworks, optimize distributed systems performance, and collaborate with research and hardware teams to advance AI capabilities. Key challenges include fault tolerance, elastic scaling, and efficient coordination of models across large-scale GPU, CPU, and LPU environments.