AI Infrastructure Specialist

EdgeQ Technologies Private Limited; United States; Remote; USD 95,000 - 155,000; Full time

Job summary

EdgeQ Technologies Private Limited in the United States is seeking an AI Infrastructure Specialist to design, build, deploy, and maintain scalable AI infrastructure supporting ML workloads. The role emphasizes cloud-based GPU computing, containerization with Docker, Kubernetes, and MLOps pipelines to ensure reliable model deployment and performance.

The ideal candidate will optimize resources, implement security controls, and collaborate with AI/ML engineers and DevOps teams while working fully

Qualifications

• 2–6 years of AI Infrastructure/DevOps experience.
• Strong knowledge of AWS, Azure, or Google Cloud.
• Hands-on with Docker and Kubernetes.
• Experience with Linux administration and scripting.
• Familiarity with ML deployment workflows.
• CI/CD and infrastructure automation experience.
• Networking, storage, and cloud security fundamentals.
• Experience with monitoring tools.

Responsibilities

• Design, deploy, and maintain scalable AI infrastructure.
• Manage cloud AI infrastructure across AWS, Azure, or Google Cloud.
• Configure and optimize GPU-based computing environments.
• Implement and maintain Kubernetes clusters and Docker containers.
• Support AI model training, deployment, and inference environments.
• Build and maintain MLOps pipelines for CI/CD.
• Monitor infrastructure performance, availability, and scalability.
• Automate infrastructure using Terraform, Ansible, or similar tools.
• Collaborate with AI engineers, ML engineers, and DevOps teams.
• Implement infrastructure security and monitoring solutions.

Skills

AWS/Azure/GCP

Docker & Kubernetes

Linux administration

Python scripting

CI/CD pipelines

Terraform/Ansible

ML deployment

Networking & security

Monitoring tools

GPU computing

Education

Bachelor's or Master's in CS/IT/Engineering

Tools

Terraform

Ansible

Triton / vLLM

Job description

Location: United States

Headquarters: United States

AI Infrastructure Specialist

Job Title: AI Infrastructure Specialist
Location: United States (Remote)
Work Mode: 100% Remote
Experience: 2–6 Years
Salary Range: $95,000 – $155,000 per year (USD)
Employment Type: Full-Time
Job Category: Artificial Intelligence / Cloud Infrastructure / DevOps

Job Summary

We are seeking a skilled and experienced AI Infrastructure Specialist to join our growing technology team in the United States. The ideal candidate will be responsible for designing, building, deploying, and maintaining scalable infrastructure to support AI and machine learning workloads.

The candidate should have strong knowledge of cloud infrastructure, GPU computing, containerization, Kubernetes, MLOps, and AI model deployment. This role involves optimizing infrastructure performance, ensuring scalability, and supporting reliable AI-powered applications.

This position offers a fully remote work opportunity for qualified candidates across the United States.

Key Responsibilities

• Design, deploy, and maintain scalable infrastructure for AI and machine learning applications.

• Manage cloud-based AI infrastructure across AWS, Microsoft Azure, or Google Cloud.

• Configure and optimize GPU-based computing environments for AI workloads.

• Implement and maintain Kubernetes clusters and Docker containers.

• Support AI model training, deployment, and inference environments.

• Build and maintain MLOps pipelines for continuous integration and deployment.

• Monitor infrastructure performance, availability, scalability, and resource utilization.

• Optimize GPU, CPU, memory, and storage resources for AI workloads.

• Implement infrastructure automation using Terraform, Ansible, or similar tools.

• Collaborate with AI engineers, ML engineers, and DevOps teams.

• Implement infrastructure security, access controls, and monitoring solutions.

• Troubleshoot infrastructure issues and ensure system reliability.

• Maintain technical documentation and infrastructure best practices.

Required Skills & Qualifications

• 2–6 years of experience in AI Infrastructure, Cloud Infrastructure, DevOps, or a related field.

• Strong knowledge of AWS, Azure, or Google Cloud platforms.

• Hands-on experience with Docker and Kubernetes.

• Understanding of GPU computing and AI workload optimization.

• Experience with Linux administration and system troubleshooting.

• Knowledge of Python, Bash, or Shell scripting.

• Familiarity with machine learning model deployment and inference workflows.

• Experience with CI/CD pipelines and infrastructure automation.

• Knowledge of Terraform, Ansible, or similar infrastructure tools.

• Understanding of networking, storage, and cloud security fundamentals.

• Experience with monitoring tools such as Prometheus, Grafana, or Datadog.

• Strong analytical, troubleshooting, and problem-solving skills.

Preferred Qualifications

• Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, or a related field.

• Experience with NVIDIA GPUs, CUDA, and GPU resource management.

• Familiarity with MLflow, Kubeflow, Ray, or similar MLOps frameworks.

• Knowledge of LLM deployment and inference optimization.

• Experience with distributed computing and high-performance computing (HPC).

• Familiarity with serverless AI infrastructure and microservices architecture.

• Understanding of model serving frameworks such as NVIDIA Triton, vLLM, or TorchServe.

• Experience managing large-scale AI infrastructure environments.

Salary & Benefits

• Annual Salary: $95,000 – $155,000 USD.

• Competitive compensation based on experience and technical expertise.

• 100% remote work opportunity.

• Flexible working arrangements.

• Health, dental, and vision insurance.

• Paid time off and holidays.

• Retirement savings benefits, where applicable.

• Professional development and technical certification support.

• Career advancement opportunities.

Work Location

United States – Fully Remote

• Candidates from eligible locations across the United States are encouraged to apply.

• Must be legally authorized to work in the United States.

• Ability to collaborate with distributed engineering teams across different US time zones.

Equal Opportunity Employer: We welcome qualified candidates from diverse professional backgrounds and encourage applications from eligible candidates across the United States.