Software Engineer - GPU Fabric Observability

Baseten · Remote

Posted
47 days ago
Last confirmed live
1 day ago

What this role involves

Build a first-class observability and root-cause analysis system for GPU fabrics at Baseten. The role involves collecting high-volume signals from network and compute components to diagnose failures in real time. The engineer will own the architecture and work at the boundary between networking and inference software.

Skills this posting asks for

  • distributed systems
  • networking
  • rdma
  • infiniband
  • roce
  • gpu
  • gpu fabric
  • telemetry
  • kubernetes
  • observability
  • root cause analysis
  • anomaly detection
  • streaming
  • correlation
  • high-performance networks
  • gpudirect
  • prefill
  • decode
  • kv cache
  • scheduler
  • serving layer
  • inference
  • switch
  • nic

Requirements

  • Level: lead

From the employer’s posting

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the front…

Read the full description on Baseten’s careers page

Apply without filling the form

Approve this role and the application is completed for you, including a résumé tailored to it. You get a confirmation when it lands, and a credit is only spent when a submission is confirmed.

Other roles at Baseten

All 14 roles at Baseten