AI Infrastructure Engineer

CloudWizz; United States; Remote; USD 140,000 - 200,000; Full time

Job summary

CloudWizz is seeking an expert to lead engagements around AI infrastructure that powers reliable production models. You will architect and maintain systems for efficient GPU compute, model serving, monitoring, and observability across the ML lifecycle.

You will drive MLOps maturity, collaborate with cross-functional teams, and translate operational needs into dependable, scalable platforms for production AI workloads.

Qualifications

• Experience designing or operating production AI infrastructure.
• Familiarity with GPU workloads, model serving and MLOps.
• Proven ability to lead technical engagements.
• Understanding of monitoring and observability for ML apps.

Responsibilities

• Lead projects involving GPU compute clusters and AI infrastructure.
• Design and support model-serving systems for production workloads.
• Establish and improve MLOps across the model lifecycle.
• Implement observability for large language model applications.

Skills

Production AI infrastructure

GPU workloads

Model serving

MLOps

Leadership & stakeholder engagement

Monitoring & observability

Tools

GPU clusters

Model serving platforms

Observability tools

Job description

Role overview

Lead engagements focused on the infrastructure that enables reliable production AI. The work spans the systems needed to run models efficiently, observe their behavior, and support repeatable machine-learning operations.

Responsibilities

• Lead projects involving GPU compute clusters and AI infrastructure.
• Design and support model-serving systems for production workloads.
• Establish and improve MLOps practices across the model lifecycle.
• Implement observability for large language model applications.

Requirements

• Experience designing or operating infrastructure for production AI systems.
• Familiarity with GPU-based workloads, model serving, and MLOps.
• Ability to lead technical engagements and translate operational needs into dependable systems.
• Understanding of monitoring and observability for machine-learning applications.