On-Prem AI Platform & GPU Infra Engineer

SG-EDTS; Jakarta Pusat; Presencial; IDR 350.000.000 - 700.000.000; Jornada completa

Descripción de la vacante

Sertis Indonesia is seeking an AI Infrastructure / Platform Engineer to own an on‑premise AI platform powered by high‑performant GPU servers in a data centre. You will prepare servers, configure environments, and deploy AI workloads while ensuring security and performance.

You will lead deployment, monitoring, and optimization efforts, enabling reliable services for clients and managing incidents with a strong focus on hardware and network reliability.

Formación

• Enthusiastic about computer hardware, GPUs, CPUs, and server infrastructure.
• Experience managing Linux servers in production with SSH, storage, networking, and security hardening.
• Hands-on GPU server experience with drivers, CUDA, and troubleshooting; AI workloads familiarity is a plus.
• Understanding of networking fundamentals, connectivity, firewalls, and security.

Responsabilidades

• Prepare and configure GPU servers after hardware installation, including OS, security, storage, and encryption.
• Deploy, configure, and maintain AI-related workloads on the on-premise platform with containerized deployments.
• Build and maintain monitoring systems, dashboards, and alerts for GPU utilization and server health.
• Conduct load and performance testing to improve platform reliability and GPU utilization.
• Diagnose and resolve issues across hardware, OS, storage, networks, and applications; document solutions.

Conocimientos

GPU servers

Linux in production

Networking basics

Bash or Python

Monitoring with Prometheus/Grafana

Herramientas

CUDA drivers

Container runtimes

Kubernetes

Ansible

Terraform

Prometheus/Grafana

Descripción del empleo

Sertis Indonesia is seeking an AI Infrastructure / Platform Engineer to own an on‑premise AI platform powered by high‑performant GPU servers in a data centre. You will prepare servers, configure environments, and deploy AI workloads while ensuring security and performance.

You will lead deployment, monitoring, and optimization efforts, enabling reliable services for clients and managing incidents with a strong focus on hardware and network reliability.