AIOps Engineer - AWS/Azure Platfrom

Job Description :

Responsibilities :

- Possess end-to-end knowledge of VLLM model hosting and inferencing.

- Advanced knowledge of public cloud platforms such as AWS and Azure.

- Build and maintain machine learning pipelines and models for predictive maintenance, anomaly detection, and noise reduction.

- Experience in production support and real-time issue handling.

- Design dashboards and visualizations to provide operational insights to stakeholders.

Skills :

- 1 to 2 years of experience with Jenkins and GoCD to make build/deploy pipelines.

- Hands-on experience with open-source and self-hosted model APIs using SDKs.

- Drive data-driven decisions by analyzing operational data and generating reports on system health, performance, and availability.

- Basic knowledge of kserve and rayserve inferencing .

- Good knowledge of high level scaling using Karpenter , Keda , System based vertical/horizontal scaling.

- Strong knowledge on linux operating system or linux certified .

- Previous experience with Helm chart deployments and Terraform template and module creation is highly recommended.