Software & DataOn site
(Staff / Senior Staff) AI Infra Engineer, Inference Infrastructure
Together AISan Francisco, CA
$250,000–320,000/yr
Posted Oct 20, 2026
What you’d do
Own production reliability of a Kubernetes-native control plane that provisions and runs a GPU inference fleet. Triage InfiniBand and RDMA stalls, diagnose model and LoRA-serving faults, and extend automated self-healing so new failure modes become permanent fixes. Found on the employer's careers page on Oct 21, 2026. Apply through the link.
You’ll need
- Experience operating a provisioning or host-lifecycle pipeline in production
- Troubleshooting stuck or failed state transitions at fleet scale
- GPU driver/CUDA validation and health checks
- Kubernetes
- InfiniBand/RDMA troubleshooting
Our summary of the listing. The full listing has the details.