AI Infrastructure / Platform Engineer

Responsibilities

THIS JOB OPPORTUNITY IS FOR OUR PARTNERING COMPANY, SERTIS INDONESIA

[About Sertis Teknologi Indonesia]

Sertis Teknologi Indonesia builds AI and data solutions for enterprises in Indonesia. We apply leading-edge research and practices to push the boundaries of what AI can do, turning them into practical, innovative solutions for our clients. We also run our own on-premise AI platform, so clients, including those in regulated industries, can use advanced AI while their data stays private and under their control.

[About the Role]

We are looking for an AI Infrastructure / Platform Engineer to build, operate, and maintain our on-premise AI platform, powered by high-performance GPU servers in a data centre.

In this role, you will take ownership of the platform end to end, from preparing physical servers and configuring system environments to deploying AI systems and applications, maintaining infrastructure security, optimizing performance, and supporting clients in production.

We are looking for someone who is passionate about hardware, understands how software runs on physical systems, has a solid foundation in networking, and enjoys solving technical challenges while delivering reliable services to clients.

[Key Responsibilities]

• GPU Server Setup & Management: Prepare and configure servers after hardware installation, including operating systems, user permissions, secure access, firewalls, storage, software RAID, and disk encryption. Maintain GPU drivers, CUDA, container runtimes, and related system components.
• System & Application Deployment: Deploy, configure, and maintain systems and applications, primarily AI-related workloads, on the on-premise platform. Manage containerized deployments, application updates, versioning, and rollbacks while ensuring secure connectivity and appropriate firewall configurations.
• Monitoring & Observability: Build and maintain monitoring systems, dashboards, and alerts for GPU utilization, server health, network performance, and application services. Establish performance baselines and identify potential issues before they affect clients.
• Performance Optimization: Conduct load and performance testing, assess platform capacity, and improve system reliability, application responsiveness, and GPU utilization within data centre power and cooling constraints.
• Troubleshooting & Incident Management: Diagnose and resolve issues across hardware, operating systems, storage, networks, and applications. Identify root causes, document solutions, and maintain clear operational procedures.
• Client Onboarding & Technical Support: Support client onboarding, access provisioning, API key management, data separation, and usage limits. Act as a technical point of contact, provide technical consultations and usage reports, and help resolve incidents in line with agreed service levels.
• Security & Infrastructure Operations: Maintain access controls, logging, encryption, backups, and security documentation. Coordinate with hardware vendors and data centre providers on maintenance, repairs, warranties, and infrastructure requirements.

Requirements

[Main Requirements]

• Are enthusiastic and passionate about computer hardware, particularly GPUs, CPUs, and server infrastructure.
• Understand how to install, configure, and run software on physical hardware, from operating systems and system services to applications.
• Have experience managing Linux servers in production, with a solid understanding of SSH, storage, networking, and security hardening.
• Have hands-on experience with GPU servers, including drivers, CUDA, and troubleshooting. Experience with AI workloads or large language model deployment is a plus.
• Understand the fundamentals of networking, connectivity, firewalls, and network security.
• Are familiar with containers and scripting using Bash or Python.
• Can build or maintain monitoring and alerting systems, such as Prometheus and Grafana, and understand how to identify meaningful metrics.
• Enjoy troubleshooting issues across hardware, operating systems, networks, and applications using logs, metrics, and system tools.
• Use innovative tools, including AI tools, to work efficiently while carefully reviewing and validating their output before production use.
• Have strong client-facing and service-oriented skills, with the ability to support onboarding, prepare technical reports, explain technical issues, and provide practical consultations.
• Communicate clearly, collaborate effectively, and take ownership of technical responsibilities in a dynamic environment.

[Nice to Have]

• Experience with multi-GPU servers, GPU interconnects, or AI inference engines such as vLLM.
• Familiarity with Kubernetes and infrastructure-as-code tools such as Ansible or Terraform.
• Experience with monitoring and observability tools, high-speed networking (100 Gbps or above), or infrastructure performance testing.
• Knowledge of infrastructure security, data privacy, or compliance standards such as ISO 27001 and financial-sector regulations.

About SG-EDTS

In the fast-paced world of technology, disruption is the norm. That's why EDTS was created - to democratize digital technology and make it accessible to everyone. And since 2019, we've been the Digital Center of Excellence for Salim Group.

Our team of digital experts is here to help companies navigate the ever-changing landscape of technology and harness its power to transform their business. Our vision is simple - to improve the welfare of the country by helping organizations achieve their full potential.

At EDTS, we're on a mission to help our clients seize new opportunities and prepare for the future by leveraging digital technology and data science. Our values of Integrity, Respect, Positive Impact, Growth, and Operational Excellence guide us in everything we do.

Join us on this journey of digital transformation, where we help companies stay ahead of the curve and achieve their goals in this rapidly changing world.