LLM Platform Engineer — AI Infra & Deployment

Kuok Group Singapore; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Kuok Group Singapore is seeking an AI Platform Engineer to build and own the infrastructure layer for all AI use cases. You will oversee the LLM gateway, deployment platform, CI/CD pipelines, model serving, observability, cost controls, and eval pipelines.

Reporting to the Principal AI Architect, you will work closely with LLM Ops and MLOps engineers to deliver scalable, observable AI platforms across cloud environments.

Qualifications

• Bachelor-level computer science or equivalent.
• Experience building and operating CI/CD pipelines and IaC.
• Hands-on with LLM infrastructure and model gateways.
• Strong Python programming and cloud familiarity.
• Experience with observability and cost-tracking for AI workloads.

Responsibilities

• Design, build, and maintain CI/CD pipelines for AI use cases.
• Own environment provisioning and infra-as-code across environments.
• Manage end-to-end deployment platform, releases, and rollback.
• Operate LLM gateway and model-serving configurations.
• Implement observability, cost telemetry, and token controls.
• Maintain prompts and model version registry for traceability.
• Instrument systems with LangSmith traces and metrics.
• Collaborate with LLM Ops/MLOps and QA teams.
• Document architecture, runbooks, and onboarding guides.
• Support eval pipelines and gate production deployments.

Skills

CI/CD pipelines

Infrastructure as code

Production deployments

Linux & Windows

Networking basics

Model gateway

LLM observability

Python

Documentation & runbooks

Cloud platforms (Azure/AWS/GCP)

Education

Bachelor in Computer Science or related

Tools

Terraform

LangSmith

Job description

Kuok Group Singapore is seeking an AI Platform Engineer to build and own the infrastructure layer for all AI use cases. You will oversee the LLM gateway, deployment platform, CI/CD pipelines, model serving, observability, cost controls, and eval pipelines.

Reporting to the Principal AI Architect, you will work closely with LLM Ops and MLOps engineers to deliver scalable, observable AI platforms across cloud environments.