Source description
About the role
Key Responsibilities: Design and implement cloud architecture for AI/ML, LLM model deployment, monitoring, and scaling Deploy models using Docker, Kubernetes, and CI/CD pipelines across cloud environments on Azure or GCP Optimize AI model serving using tools like TensorFlow Serving, TorchServe, ONNX Runtime, Triton Inference Server, etc. Build and manage IaC using Terraform, or CloudFormation Implement security best practices, autoscaling, logging, monitoring (Prometheus/ Grafana/ ELK), and disaster recovery plans Collaborate with ML engineers to produce prototypes into resilient, cloud-native services Benchmark and tune deployments for low latency, high throughput, and cost optimization Required Qualifications: 8+ years of experience in cloud engineering, with 4+ years focused on AI/ML deployment at scale Strong hands-on expertise in Azure and GCP Proficient in Docker, Kubernetes, Helm, and serverless deployment models Solid understanding of ML frameworks (TensorFlow, PyTorch, scikit-learn) and model deployment workflows Experience in CI/CD tools (GitHub Actions, Jenkins, GitLab CI), scripting (Python, Bash), and API gateway management
More at E Solutions