Cloud Orchestration Engineer for Scalable AI Inference

INFERACT SINGAPORE PTE. LTD.; Penarth; On-site; GBP 119,000 - 198,000; Full time

Benefits offered by this job

Equity

Medical coverage

Dental coverage

Vision coverage

Job summary

Inferact SINGAPORE PTE. LTD. is seeking a cloud orchestration engineer to design and operate the systems that keep vLLM running reliably at scale.

You will build cluster management, deployment automation, and production monitoring to enable teams worldwide to serve AI models with minimal friction. The role requires Kubernetes expertise, experience with custom operators, and proficiency in Python/Rust/Go, plus Terraform and Helm for infrastructure automation.

Qualifications

• Bachelor’s degree or equivalent in CS/Engineering.
• Experience with Kubernetes at scale.
• Proficiency in Python, Rust or Go.
• Experience with GPU clusters and cloud/on-prem infra.

Responsibilities

• Design cluster management systems and deployment automation.
• Build production monitoring and observability tooling.
• Ensure recoverability and debuggability of vLLM deployments at scale.
• Collaborate across teams to simplify operational complexity.

Skills

Kubernetes at scale

Kubernetes Operators

Python/Rust/Go

Cloud platforms AWS/GCP/Azure

GPU Clusters management

Multi-cloud / On-prem infra

Education

Bachelor's degree or equivalent

Tools

Terraform

Helm

Job description

Inferact SINGAPORE PTE. LTD. is seeking a cloud orchestration engineer to design and operate the systems that keep vLLM running reliably at scale.

You will build cluster management, deployment automation, and production monitoring to enable teams worldwide to serve AI models with minimal friction. The role requires Kubernetes expertise, experience with custom operators, and proficiency in Python/Rust/Go, plus Terraform and Helm for infrastructure automation.