Position : Senior DevOps, MLOps & AIOps Engineer (Azure)

Location : Delhi/NCR

Work Experience : 4+ years

About Antino :

With the intention and conviction of emerging as an unparalleled IT Digital Transformation Services platform, we at Antino Labs are known for providing impeccable software services using cutting edge technology across the globe. Without ever compromising with the quality of our output and bringing talent and diligence on a common platform, we have been noticed for our efficiency and reliability. With dynamic exposure to the industry, we believe in refining and redefining our standard according to the changes in the market's requirement. Our multiple years of experience in the industry has enabled us to register our global presence. Presently, our branch offices are in Bangalore, UK, Dubai, Canada, and the US.

Role Overview :

We are seeking a hands-on Senior Engineer to design, scale, and operate high-performance AI infrastructure and cloud platforms on Microsoft Azure. You will bridge traditional DevOps with modern MLOps and AIOpsmanaging production GPU clusters, automating model deployment pipelines (vLLM, Ray, Triton), and embedding intelligent observability across multi-environment Azure Kubernetes Service (AKS) platforms hosting AI-driven applications.

Key Responsibilities :

- Provision, scale, and optimize NVIDIA GPU-accelerated node pools on Azure Kubernetes Service (AKS). Configure CUDA runtime environments, drivers, TensorRT optimization, and NVIDIA DCGM monitoring.

- Architect scalable model inference and fine-tuning deployment pipelines using Azure Machine Learning, Kubeflow, or MLflow. Deploy and tune high-throughput LLM serving platforms (vLLM, Ray Serve, Triton Inference Server).

- Implement comprehensive infrastructure and application observability (Prometheus, Grafana, OpenInference, Phoenix/LangSmith). Monitor GPU memory/compute utilization, model latency, token metrics, vector database performance (Pinecone, Milvus, Qdrant), and cost drift.

- Author secure, enterprise-ready IaC using Terraform or Bicep. Configure Azure enterprise networking (Hub-and-Spoke VNets, Private Endpoints) and security governance (Microsoft Entra ID, Azure Policy, Key Vault).

- Build multi-stage deployment pipelines in Azure DevOps or GitHub Actions, embedding container security scanning, policy compliance, and automated canary/blue-green deployment strategies.

Mandatory Eligibility & Technical Gates :

- Strictly 4 years of combined professional experience in DevOps, Cloud Infrastructure, or Systems Engineering.

- Direct hands-on experience with GPU workload scheduling on K8s/AKS, NVIDIA CUDA driver configurations, TensorRT optimization, or vLLM/Triton GPU deployment.

- Deep working knowledge of Azure Kubernetes Service (AKS), Node Pools, VNets, Azure Storage (Blob/Files), Entra ID RBAC, and Azure Container Registry.

- Advanced skills in Terraform or Bicep/ARM for automated multi-environment provisioning.

- Hands-on creation and management of production pipelines in Azure DevOps Pipelines or GitHub Actions.

Preferred Skills & Qualifications :

- Practical exposure to vector database deployment and scaling (Milvus, Qdrant, Pgvector).

- Experience with LLM observability, prompt tracking, and AI safety guardrails.

- Certifications : Microsoft Certified : Azure DevOps Engineer Expert (AZ-400) or Azure Solutions Architect Expert (AZ-304/AZ-305).