jobs
(Senior/Junior AI Inference Reliability Engineer, Compute Infra
About the Role We're looking for a software engineer, reliability-minded but still a builder, to own what happens in production to the Kubernetes-native control plane that provisions and runs our GPU…
Auf Englisch
- Company
- Together AI
- Location
- San Francisco
- Status
- Open
- Posted
- 2026-10-27 19:36 UTC
A reliability-focused software engineering role on Together AI's compute infrastructure team, maintaining the Kubernetes-based control plane that provisions and runs a GPU inference fleet. The work covers production incidents, InfiniBand/RDMA and GPU driver/CUDA faults, model- and LoRA-serving failures, SLOs and error budgets, and automation that turns new failure modes into permanent fixes. The posting asks for production reliability experience on large distributed or GPU-serving systems, Kubernetes controllers and CRDs, and hands-on networking troubleshooting. It stands out for combining incident response with building remediation plugins and reliability tooling.
Original job posting