Site Reliability Engineer

Job Title : Site Reliability Engineer (SRE) – Azure & AI

Experience : 7+ years

Work Mode : Hybrid

Work Location : Chennai / Mumbai / Gurgaon

Job Summary :

We are looking for an experienced Site Reliability Engineer (SRE) with strong expertise in Microsoft Azure , AI infrastructure , and automation . The ideal candidate will have a solid background in managing cloud environments using GitHub / Azure DevOps , and hands-on experience in AI model deployment and scaling . This role involves working closely with engineering teams to deliver reliable, secure, and scalable cloud infrastructure that supports AI workloads and enterprise applications.

Key Responsibilities :

• Design, build, and maintain scalable cloud infrastructure on Microsoft Azure .
• Automate infrastructure provisioning and deployment using Terraform , Argo , and Helm .
• Manage and optimize Azure Kubernetes Service (AKS) for AI and microservices workloads.
• Support AI model hosting using frameworks such as Huggingface Transformers , vLLM , or Llama.cpp on Azure OpenAI , VMs , or GPUs .
• Implement CI / CD pipelines using GitHub Actions and integrate with JFrog Artifactory .
• Monitor and maintain system performance and reliability using Grafana , ensuring proactive issue resolution.
• Collaborate with development teams to align infrastructure with application requirements.
• Enforce networking and information security best practices .
• Manage and optimize caching and data layer performance using Redis .

Required Skills & Technologies :