LLM Platform Engineer - AI Inference & Ops

Nanyang Technological University Singapore; Singapore; On-site; SGD 90,000 - 140,000; Full time

Job summary

NTU (Nanyang Technological University Singapore) hosts the AI Engineer role within the AISG Platform team to design and optimize LLM inference workflows and support the deployment of customized AI solutions. You will contribute to production-grade AI infrastructure, including GPU-enabled systems and RAG services, collaborating with internal teams across NTU and AISG.

The role emphasizes managing multi-cloud platforms, building scalable API services, and maintaining observability and automation

Qualifications

• Requires a degree in Computer Science, Information Technology, or equivalent.
• 1–3 years of DevOps, SRE, or platform engineering experience with production-scale systems.
• Hands-on experience with IaC (Terraform), containers and orchestration (Docker, Kubernetes), and managed compute/storage networks.

Responsibilities

• Own day-to-day operations of SEA-LION API Farm across multi-cloud environments, monitoring health, GPU capacity, performance and security posture.
• Optimize LLM inference across modalities to deliver business value and meet production goals.
• Diagnose and troubleshoot performance and reliability issues in API Farm and related services.
• Build new API services such as batch API services and MCP-based services.

Skills

Python

Bash

Strong communication

CI/CD fundamentals

Education

Bachelor’s degree in Computer Science, Information Technology, or equivalent

Tools

Terraform

Docker

Kubernetes

Job description

NTU (Nanyang Technological University Singapore) hosts the AI Engineer role within the AISG Platform team to design and optimize LLM inference workflows and support the deployment of customized AI solutions. You will contribute to production-grade AI infrastructure, including GPU-enabled systems and RAG services, collaborating with internal teams across NTU and AISG.

The role emphasizes managing multi-cloud platforms, building scalable API services, and maintaining observability and automation