Baseten is building the global OS for distributed AI hardware. We seek a foundational engineer to lead GPU networking, co-optimizing communication and compute for disaggregated serving and WideEP. You will blend open-source tech with custom kernels to push wire-speed data movement. Join Baseten to shape the next era of scalable AI inference across H100/H200 GPUs and NVL72 racks, delivering low-latency, high-throughput performance at scale.