Senior Software Engineer, RL Post-Training Frameworks
Architect and build scalable reinforcement learning post-training infrastructure that operates across GPUs, CPUs, and LPUs, optimizing training-inference-rollout loops for performance and efficiency. Contribute to open-source RL frameworks and distributed runtimes, collaborate with researchers and hardware teams, and ensure fault tolerance and elastic scaling in large-scale distributed systems. Work spans system design, runtime optimization, and cross-team advocacy to support next-generation AI workloads.