Cloud Orchestration Engineer for Scalable ML Inference

INFERACT SINGAPORE PTE. LTD.; Singapore; On-site; SGD 167,000 - 335,000; Full time

Benefits offered by this job

Medical coverage

Dental coverage

Vision coverage

Equity

Job summary

Inferact is seeking a Cloud Orchestration Engineer to scale vLLM deployments across multi-cloud and on-prem environments. You’ll design cluster management, deployment automation, and production monitoring to keep AI models running reliably at scale.

Ideal candidates have Kubernetes expertise, experience building operators, and proficiency in Python, Rust, or Go with IaC tooling. Fresh graduates welcome to apply.

Qualifications

• Bachelor's degree or equivalent in CS/engineering.
• Experience with Kubernetes at scale, and deploying operators.
• Proficiency in Python, Rust or Go and IaC tools (Terraform, Helm, etc).
• Experience managing GPU clusters and multi-cloud/on-prem infra.
• Ability to design and operate custom Kubernetes operators.

Responsibilities

• Design cluster management and deployment automation at scale.
• Build production monitoring and observability to reduce downtime.
• Ensure reliable, debuggable and recoverable vLLM deployments.
• Collaborate with global teams to support AI model serving.
• Optimize GPU scheduling and resource usage across platforms.

Skills

Kubernetes

Container Orchestration

Kubernetes Operators

Python

Go

Rust

Terraform

Helm

GPU Clusters

Cloud Platforms

Education

Bachelor's degree or equivalent experience in CS/engineering

Tools

Terraform

Helm

Job description

Inferact is seeking a Cloud Orchestration Engineer to scale vLLM deployments across multi-cloud and on-prem environments. You’ll design cluster management, deployment automation, and production monitoring to keep AI models running reliably at scale.

Ideal candidates have Kubernetes expertise, experience building operators, and proficiency in Python, Rust, or Go with IaC tooling. Fresh graduates welcome to apply.