Senior Deployment Engineer with LLM and GPU Infrastructure experience

Summary

We are seeking an Infrastructure Engineer for Air-gapped LLM Deployments to support secure, large-scale software deployments in GPU-based environments. The role focuses on deploying LLM workloads in air-gapped settings and establishing observability with Grafana and Prometheus, with onsite presence in Riyadh required for two weeks per month.

General information

They need a senior engineer who can take ownership of complex deployments across isolated or air-gapped environments. The role will involve working with GPU infrastructure for LLM workloads and ensuring systems can be deployed, monitored, and maintained reliably at scale.

The engineer should be comfortable troubleshooting infrastructure and deployment issues, automating deployment processes, and working with observability platforms such as Grafana and Prometheus.

Location: Riyadh, Saudi Arabia
Onsite requirement: A few times per quarter in Riyadh

Tasks and Deliverables

Design and support air-gapped deployment environments for LLM-based systems.

Deploy and optimize LLM workloads on GPU infrastructure.

Support large-scale software deployments across secure environments.

Implement and maintain observability using Grafana and Prometheus.

Collaborate onsite in Riyadh to assess, deploy, and troubleshoot environment-specific issues.

Required experience

Expertise in air-gapped deployments.

Experience with large-scale software deployments.

Experience deploying LLMs on GPUs.

Hands-on experience with Grafana and Prometheus.

Engagement highlights

Senior-level infrastructure/deployment engineering role.

Work on large-scale GPU and LLM infrastructure.

Challenging deployment scenarios involving air-gapped environments.

Full-time, long-term position