AI Infrastructure / Server Engineer

We are looking for a skilled Server Engineer to design, setup, configure, optimize, and maintain server infrastructure (on-premise / hybrid / cloud) to run Python-based Agentic AI applications in a high-availability, secure, and scalable production environment.

Responsibilities

Design and implement server infrastructure for AI/ML production environments.

Install, configure, and maintain Linux-based servers (Ubuntu, CentOS, RHEL).

Set up and optimize GPU servers for AI workloads.

Configure storage systems (RAID) and manage server resources efficiently.

Manage network configurations including VLANs, firewalls, and load balancers.

Deploy and optimize AI/ML applications using containerization and orchestration tools.

Ensure infrastructure reliability, scalability, and security.

Monitor system performance and perform ongoing optimization and maintenance.

Requirements

Education: Bachelor’s degree in Informatics Engineering, Information Systems, Electrical Engineering, Computer Science, or a related field.

Experience: 2–5 years of experience.

Technical Skills (Mandatory) Infrastructure & Server Setup

Strong experience in Linux server installation and configuration (Ubuntu / CentOS / RHEL).

Experience setting up rack servers / blade servers.

RAID configuration and storage management.

Network configuration (VLAN, firewall, load balancer).

AI/ML Infrastructure

Setup and configuration of CUDA, cuDNN, and NVIDIA drivers.

GPU utilization optimization.

FastAPI or Flask.

Gunicorn or Uvicorn.

Model serving using Triton, TorchServe, or custom APIs.

Nice to Have

Certifications such as Cloud (AWS / Azure / GCP Associate or Professional).

Security (CEH / CompTIA Security+).

Experience managing hybrid or multi-cloud environments.

Experience implementing infrastructure security best practices for AI workloads.

DevOps & Production Readiness

CI/CD pipeline (GitLab CI / GitHub Actions / Jenkins).

Infrastructure as Code (Terraform / Ansible).

SSL/TLS configuration.

Backup & disaster recovery strategy.

High Availability & auto-scaling design.

Security & Governance

IAM & access control.

Secrets management (Vault / environment isolation).

Compliance readiness (e.g., HIPAA-like, ISO 27001, PDP).

Monitoring & Observability

ELK Stack.

Alerting system (PagerDuty / custom webhook).

About the Company Steradian Data Optima is a fast growing IT company based in Jakarta with products and services including software development and data management. Our vision is to become the big 5 IT consultants in ASEAN, Japan, Middle East and Australia. We are hiring best talent to grow with us.

#J-18808-Ljbffr