AI Model Deployment Engineer

About the Role

We are seeking an experienced MLOps Engineer to design, build, and maintain scalable machine learning infrastructure with strong focus on Azure cloud ecosystem. You will deploy and optimize ML / AI models in production, with emphasis on GPU-accelerated workloads and large language models.

Key Responsibilities

• Design and implement MLOps pipelines using Kubeflow and KServe for model deployment and serving
• Deploy and manage production ML models on Kubernetes with NVIDIA GPU acceleration
• Optimize model inference using vLLM, TensorRT-LLM, Triton Inference Server , and PyTorch Dynamo
• Implement auto-scaling using KEDA, HPA , and Azure Cluster Autoscaler
• Build CI / CD pipelines using Azure DevOps for automated ML model deployment
• Manage Azure infrastructure (AKS, Azure ML, Container Registry) using IaC (Terraform / ARM / Bicep)
• Implement monitoring and observability using Prometheus and Grafana
• Perform Linux system administration and optimize containerized workloads
• Deploy and manage LLM applications with OpenAI API and Azure OpenAI services
• Monitor GPU utilization, model performance, and implement drift detection
• Build RAG systems and manage vector databases for LLM applications