(Senior/Junior AI Inference Reliability Engineer, Compute Infra

Role

This role involves owning the production reliability of a Kubernetes-native GPU inference fleet, including managing the provisioning state machine and extending automated self-healing systems. Candidates must have hands-on experience with large-scale distributed systems, InfiniBand/RDMA troubleshooting, and Kubernetes controller/CRD patterns.

Location: San Francisco
Employment: full time
Work pattern: unspecified
Seniority: unspecified

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Greenhouse feed. Source update: 2026-10-27T15:38:38-04:00. Check the employer’s page for the complete description, current availability and application terms.

• job-boards.greenhouse.io/togetherai/jobs/5268939007 ↗

Together AI RESEARCH PROFILE ↗