jobs

[Junior / Senior / Staff] Software Engineer, Inference / Compute Infrastructure Engineering

About the Role We're looking for a software engineer to build the Kubernetes-native control plane that provisions and runs our GPU inference fleet. You'll design a manifest-driven API where the inference team declares what they need, whethe

Company

Together AI

Location

San Francisco

Status

Open

Posted

2026-07-16T16:58:09+00:00

A software engineering role on the compute infrastructure side of an AI cloud, building the Kubernetes-native control plane behind a GPU inference fleet. The work covers a manifest-driven API and controllers for provisioning, a host lifecycle state machine from discovery to decommission, automated node health checks and remediation, plus defragmentation, rebalancing and bin-packing to raise GPU utilization. The posting hires at junior, senior or staff level and asks for real software experience in Go, Python or Rust, Kubernetes controllers or operators, durable workflow engines such as Temporal, and event-driven systems; on-call ownership is expected.