AI Infra Engineer: GPU Cloud & ML Platform

Tencent; Kuala Lumpur; On-site; MYR 120,000 - 180,000; Full time

Job summary

Tencent in Kuala Lumpur is seeking an AI Infra Engineer to design, deploy, and operate GPU-based AI infrastructure. The role focuses on backend engineering, ML engineering, and MLOps, with hands-on work on model training, inference deployment and cloud platforms.

You will work with algorithm teams to optimize AI workloads, manage GPU clusters on AWS and Kubernetes, and build pipelines for development and production environments.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, or related fields.
• 1+ years of relevant working experience in Backend Engineering, Machine Learning Engineering, MLOps, Cloud Engineering, or related fields.
• Strong programming experience in Python.
• Experience with Linux systems, Docker, and Kubernetes (K8s).
• Hands-on experience with cloud platforms, preferably AWS.
• Experience with AI model training, inference deployment, or ML production environments is highly preferred.
• Familiarity with AI/ML frameworks such as PyTorch, DeepSpeed, Megatron, vLLM.
• Understanding of Large Language Model (LLM) training/inference workflows and distributed training concepts is a plus.
• Experience with GPU computing environments, resource scheduling, or AI infrastructure operation is highly preferred.

Responsibilities

• Operate and maintain GPU-based AI infrastructure, including AWS cloud and bare-metal GPU Kubernetes (K8s) clusters.
• Support GPU cluster setup, monitoring, troubleshooting, and incident resolution.
• Develop and maintain tools related to AI computing resource management and scheduling.
• Support algorithm teams in deploying, running, and optimizing AI model training and inference services.
• Improve AI workload efficiency through infrastructure optimization and automation.
• Build and maintain ML infrastructure pipelines to support AI development and production environments.
• Collaborate with engineering and algorithm teams to improve AI platform reliability and performance.

Skills

Backend Engineering

Machine Learning Engineering

MLOps

Python

Linux

Docker

Kubernetes

AWS

AI model training

inference deployment

ML production environments

LLM training/inference workflows

Education

Bachelor’s degree in Computer Science or related fields

Tools

PyTorch

DeepSpeed

Megatron

vLLM

Job description

Tencent in Kuala Lumpur is seeking an AI Infra Engineer to design, deploy, and operate GPU-based AI infrastructure. The role focuses on backend engineering, ML engineering, and MLOps, with hands-on work on model training, inference deployment and cloud platforms.

You will work with algorithm teams to optimize AI workloads, manage GPU clusters on AWS and Kubernetes, and build pipelines for development and production environments.