On-Prem AI Platform Engineer — GPU Infra

EDTS; Jakarta Pusat; Presencial; IDR 279.000.000 - 468.720.000; Jornada completa

Descripción de la vacante

Sertis Teknologi Indonesia seeks an AI Infrastructure / Platform Engineer to build, operate, and maintain an on-premise AI platform powered by high‑performance GPU servers in a data centre. You will own the platform end to end, from configuring servers to deploying AI systems, ensuring security and reliability for client workloads.

The role requires a passion for hardware, solid networking fundamentals, and the ability to solve complex technical challenges while delivering dependable services to

Formación

• Experience managing Linux servers in production.
• Hands-on with GPU servers, drivers, CUDA.
• Knowledge of networking, firewalls, security hardening.
• Ability to deploy AI workloads on-premise platform.
• Familiar with containerized deployments and DevOps tools.
• Strong client-facing and report-writing skills.

Responsabilidades

• GPU server setup, OS config, and security.
• Deploy and maintain on-premise AI platforms.
• Monitor, alerting, and observability for GPU utilization.
• Performance optimization within data centre constraints.
• Troubleshoot hardware, OS, network, and apps.
• Onboard clients and provide technical consultations.
• Coordinate with data centre vendors for maintenance.

Conocimientos

GPU servers

Linux admin

Networking basics

Security hardening

Python scripting

Container runtimes

Prometheus

Grafana

Kubernetes

Terraform

Ansible

Herramientas

Prometheus

Grafana

Kubernetes

Terraform

Ansible

Descripción del empleo

Sertis Teknologi Indonesia seeks an AI Infrastructure / Platform Engineer to build, operate, and maintain an on-premise AI platform powered by high‑performance GPU servers in a data centre. You will own the platform end to end, from configuring servers to deploying AI systems, ensuring security and reliability for client workloads.

The role requires a passion for hardware, solid networking fundamentals, and the ability to solve complex technical challenges while delivering dependable services to