Software Engineer- GPU Fabric Observability

Build observability and root-cause analysis for Baseten’s large-scale GPU fabric used for high-density AI inference. You’ll collect high-volume telemetry from switches, hosts, probes, and inference services, correlate signals in real time, map topology and ownership, and produce evidence-based diagnoses during unfolding incidents. This is a distributed-systems challenge at the boundary of networking and inference, spanning RDMA, GPUDirect, KV cache movement, and workload backpressure.