DevOps Engineer – Cloud Infrastructure & Platform Reliability

About the role

We are seeking a proactive DevOps Engineer to design, build and operate our cloud infrastructure on AWS. The role focuses on platform reliability, automation and supporting GPU‑accelerated workloads for AI models.

Key responsibilities

• Own AWS infrastructure using Terraform (VPC, EKS, RDS, ElastiCache, ECR, IAM, VPN, PrivateLink).
• Operate Kubernetes clusters (EKS), manage workloads, Helm charts, node groups (including GPU), RBAC and ingress.
• Develop and maintain CI/CD pipelines with GitHub Actions, Docker Buildx and OIDC‑based AWS authentication.
• Manage networking and edge services such as ALB, NLB, API Gateway/Kong, TLS, DNS and private connectivity.
• Implement secrets and access controls using Vault, AWS KMS, IRSA and least‑privilege IAM policies.
• Support GPU/LLM workloads, model deployment and scaling on vLLM.
• Provide observability through OpenTelemetry, logging, alerting and incident handling.
• Collaborate with product teams for onboarding and platform usage while ensuring safe production practices.

Required profile

• 4+ years of DevOps, Platform or SRE experience.
• Strong hands‑on expertise with AWS services (VPC, EC2, EKS, IAM, RDS, S3, etc.).
• Deep knowledge of Kubernetes operations and troubleshooting.
• Proficiency in Terraform for infrastructure as code.
• Experience building CI/CD pipelines with GitHub Actions and Docker.
• Solid Linux command‑line skills (Bash, AWS CLI, kubectl).
• Understanding of networking fundamentals (DNS, TLS, load balancing).
• Experience with secrets management tools (Vault, AWS Secrets Manager).
• Clear written communication skills.

Required skills

• AWS
• Terraform
• Kubernetes / EKS
• GitHub Actions
• Docker / Docker Buildx
• Bash
• Linux
• AWS CLI
• kubectl
• Helm
• Vault
• KMS
• IRSA
• ALB / NLB
• API Gateway / Kong
• VPC / PrivateLink
• RDS PostgreSQL
• ElastiCache / Valkey
• S3
• OpenTelemetry
• OpenObserve
• GPU EKS node groups
• vLLM