DevOps/Cloud/Infrastructure Engineer

About the role

We are looking for an experienced DevOps/Cloud/Infrastructure Engineer to design, develop, deploy and scale our LLM‑powered applications across cloud (AWS) and on‑premise environments. The role bridges advanced micro‑services architecture with AI workloads, ensuring reliable operation on both managed Kubernetes (EKS) and self‑hosted clusters.

Key responsibilities

• Design and implement scalable micro‑services platforms and LLM inference pipelines on AWS and bare‑metal servers.
• Build and maintain robust CI/CD pipelines using GitHub Actions and automate deployments with Helm.
• Manage Kubernetes clusters (EKS and self‑hosted), including scaling, monitoring, and GPU orchestration.
• Collaborate with solution architects to define infrastructure as code using Terraform or Ansible.

Required profile

• Proven experience with Kubernetes in both cloud‑managed and self‑hosted environments.
• Strong background in cloud infrastructure, especially AWS, and micro‑services architecture.

Required skills

• Kubernetes (EKS, self‑hosted), Helm, GitHub Actions.
• AWS services and best practices.
• Git version control.
• Python or Go programming for operators and automation.
• Infrastructure as Code tools such as Terraform or Ansible (preferred).
• GPU orchestration with NVIDIA device plugins (preferred).