jobs

Staff Software Engineer, Inference / Compute Infrastructure Engineering London or Amsterdam

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

London & Amsterdam

Status

Open

Posted

2026-08-20T08:03:52+00:00

Together AI is hiring a staff software engineer to build the Kubernetes-native control plane behind its GPU inference fleet. The work covers a host provisioning state machine, declarative self-service APIs the inference team calls directly, self-healing automation, and scheduling and defragmentation logic that lifts GPU utilisation. The posting wants Go, Python or Rust experience, durable workflow orchestration such as Temporal, Kubernetes controllers and event-driven systems; bare-metal provisioning and GPU cluster stacks like NCCL and CUDA are nice to have. The role is on-site and owns its software in production.