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. You'll optimize distributed systems for performance, fault tolerance, and efficiency, working closely with AI researchers and contributing to open-source frameworks like VeRL, Miles, and TorchTitan. The role emphasizes deep collaboration across teams to advance AI capabilities through systems innovation.