RL Post-Training Systems Architect (Equity Eligible)

NVIDIA seeks an engineer to architect and scale RL post-training infrastructure from experimentation on a single GPU to production across thousands of nodes. You will optimize training-inference loops on GPUs, CPUs, and LPUs while improving open-source RL frameworks and partnering with cross-team groups.

The role requires expertise in distributed systems, Python and C/C++, and experience delivering production-grade runtime frameworks at large AI labs or hyperscalers. Hybrid work is supported.