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

We are looking for a software engineer to build the Kubernetes-native control plane that provisions and runs our GPU inference fleet. You will design a manifest-driven API, build controllers and reconciliation loops, and create a self-service API for the inference team. The role involves automating self-healing, defragmentation, and bin-packing to improve GPU utilization. Strong candidates have experience with Kubernetes controllers, platform APIs, and GPU scheduling.

Core requirements: strong software engineering background in Go, Python, or Rust; experience with durable workflow orchestration (Temporal, Cadence); experience building software control planes with Kubernetes controllers; experience with event-driven systems (Kafka, NATS, SQS); product mindset. Nice-to-have: bare-metal provisioning, GPU cluster stacks, hyperscaler experience.