AI Infrastructure Engineer - Remote Position

About the Role

We are looking for an AI Infrastructure Engineer to join our team remotely. In this role, you will focus on building and optimizing on-premise infrastructure that supports AI workloads. As an AI Infrastructure Engineer, you will ensure high performance, reliability, and scalability of mission-critical platforms.

What You'll Do

• Deploy and operate AI/LLM workloads on GPU-based systems, particularly in NVIDIA environments.
• Run and optimize inference servers using frameworks like vLLM and Triton.
• Design and develop production-grade APIs (FastAPI / gRPC / REST) for AI services.
• Architect asynchronous systems using queues, workers, and distributed pipelines.
• Monitor GPU utilization, memory, and system performance for efficient AI execution.
• Manage and maintain on-premise infrastructure including servers, storage, and networking systems.
• Implement and support virtualization platforms such as VMware or Hyper-V.
• Troubleshoot hardware, network, and system-related issues effectively.

Requirements

• 1-5 years of experience in infrastructure engineering, system administration, or backend systems.
• Strong knowledge of Linux and Windows server environments.
• Hands-on experience with GPU-based systems or compute-intensive workloads.
• Proficient in Python; knowledge of Golang is a plus.
• Understanding of distributed systems and asynchronous processing.
• Experience with Docker or containerized environments.
• Ability to analyze and optimize system performance (latency, throughput, cost).
• Familiarity with virtualization technologies such as VMware or Hyper-V.

Nice to Have

• Experience working in data center environments.
• Basic scripting knowledge (Shell, Python, or PowerShell).
• Familiarity with monitoring and infrastructure management tools.

What We Offer

• Work on enterprise-grade infrastructure and mission-critical systems.
• Fully remote work setup with flexible collaboration.
• Health insurance coverage.
• Opportunities for international travel based on project needs.
• Growth opportunities in AI infrastructure and system engineering.