AI Engineer

About the role

Unicloud is hiring an AI Engineer to deploy, manage, monitor, and troubleshoot GPU-based AI applications and services. The role focuses on AI infrastructure, Linux, Docker, Kubernetes, GPU monitoring,… Subscribe to Premium to view the full description and apply.

Responsibilities

• Deploy, update, restart, and manage GPU-based AI applications and services.
• Monitor AI services, APIs, application logs, performance, and availability.
• Monitor GPU health, utilization, VRAM, temperature, power usage, and processes.
• Monitor CPU, RAM, disk, and other infrastructure resources.
• Troubleshoot application crashes, deployment failures, GPU issues, and service-related problems.
• Perform Linux server health checks and troubleshooting.

Requirements

• Strong troubleshooting and analytical skills with a structured approach to problem-solving.
• Comfortable working with Linux, logs, monitoring tools, and command-line environments.
• Hands-on exposure to NVIDIA GPUs and GPU monitoring tools.
• Familiarity with AI/LLM applications and AI serving platforms such as vLLM.
• Working knowledge of Docker and Kubernetes.
• Exposure to Prometheus and Grafana.

Required Skills