The project is for one of the world's famous science and technology companies in pharmaceutical industry, supporting initiatives in AWS, AI and data engineering, with plans to launch over 20 additional initiatives in the future.
We are seeking a highly skilled Cloud Engineer to lead the infrastructure design, deployment, and operations of the AI agent orchestration platform on AWS. This role is responsible for building and managing a Kubernetes-native, enterprise-grade platform that supports scalable AI agent workloads across development, QA, and production environments.
Responsibilities
- Design, provision, and manage AWS infrastructure using Terraform, aligned with the AWS Well-Architected Framework.
Core services include:
- Amazon EKS
- VPC
- IAM
- Route 53
Own and operate EKS clusters end-to-end
Managed node group lifecycle management:
- Karpenter-based autoscaling
- Cluster add-on lifecycle upgrades
- IRSA (IAM Roles for Service Accounts) configuration
- Multi-AZ high availability and resilience
CI/CD & GitOps
Build and maintain automated deployment pipelines using:
- GitHub Actions
- ArgoCD (GitOps)
Implement release strategies:
Security & Compliance
Integrate AWS-native security and governance controls:
- AWS WAF
- GuardDuty
- Security Hub
- KMS (encryption)
- Secrets Manager
- External Secrets Operator
Enforce policy controls using:
Observability & Monitoring
Implement and manage observability stack:
- Amazon Managed Prometheus
- Amazon Managed Grafana
- CloudWatch Container Insights
- AWS X-Ray (distributed tracing)
AI/ML Integration
Leverage AWS AI/ML services to support agent orchestration:
- Cost Optimization (FinOps)
- Spot Instances
- Savings Plans
- Karpenter bin-packing strategies
- Scheduled scale-to-zero for non-production environments
Platform & Engineering Collaboration
Partner with platform and ML teams to:
- Integrate MCP servers and execution frameworks
- Support extensibility of the agent ecosystem
Skills
Must have
- 4+ years of hands-on AWS experience
AWS Certifications:
- Required: AWS Solutions Architect (Associate or Professional)
- Preferred: DevOps Engineer, Security Specialty Kubernetes & EKS Expertise
Strong hands-on experience with:
- EKS cluster provisioning and operations
- Managed node groups and Karpenter
- Kubernetes RBAC and network policies Infrastructure as Code (Terraform)
Advanced Terraform capabilities:
- Remote state management (S3 + DynamoDB)
- Security scanning (Checkov, tfsec) AWS Services Proficiency
Deep knowledge of:
- EKS, ECR, ALB, Route 53, ACM
- IAM, KMS, Secrets Manager
- IAM Identity Center
- CloudTrail, AWS Config
- GuardDuty, Security Hub, AWS WAF AI/ML Exposure
Practical experience with:
- SageMaker (model deployment and endpoints)
- Comprehend (NLP and PII detection) DevOps & Identity
Experience with:
- GitOps tools (ArgoCD or Flux)
- CI/CD pipelines for container workloads
- GitHub Actions → AWS
- EKS OIDC provider integration Observability & Debugging
Familiarity with:
Strong understanding of:
- Pod Security Standards
- Admission webhooks
- Service account least-privilege principles
Nice to have
- Experience with AI agent frameworks: LangChain, Claude Agent SDK, or similar
- Knowledge of emerging protocols: A2A (Agent-to-Agent)
- Familiarity with: Amazon Bedrock Agents, Knowledge Bases, Guardrails