About the Role We are looking for a highly skilled Senior DevOps / Cloud Platform Engineer with 5–8 years of experience in designing, deploying, and managing secure, scalable, and highly available cloud infrastructure on AWS. The ideal candidate will have extensive hands-on experience with AWS, Amazon EKS, Kubernetes, CI/CD automation, infrastructure as code, and cloud security. This role also requires experience supporting AI workloads, including deploying and optimizing Large Language Models (LLMs) on CPU and GPU infrastructure. You will work closely with software engineers, AI/ML engineers, architects, and security teams to build and maintain cloud platforms that are secure, resilient, cost-efficient, and compliant with SOC 2 and HITRUST requirements. Key Responsibilities Cloud Infrastructure Design, deploy, and manage scalable, highly available, and secure AWS infrastructure. Architect cloud environments capable of supporting enterprise-scale applications and AI workloads. Optimize infrastructure for performance, reliability, scalability, and cost. Implement high availability, disaster recovery, backup, and failover strategies. Design multi-environment infrastructure (Development, QA, UAT, Production). Kubernetes & Container Platform Design, deploy, and manage production-grade Kubernetes clusters using Amazon EKS. Optimize Kubernetes workloads for high availability and resource utilization. Configure namespaces, RBAC, network policies, autoscaling, ingress controllers, and service meshes where applicable. Troubleshoot Kubernetes networking, scheduling, storage, and performance issues. Manage rolling deployments, blue-green deployments, and canary releases. AWS Services Strong hands-on experience with: Amazon EKS Amazon EC2 Auto Scaling Groups Elastic Load Balancer (ALB/NLB) Amazon S3 Amazon RDS AWS Lambda Amazon ECR Amazon CloudWatch IAM Route 53 VPC NAT Gateway Security Groups AWS WAF AWS Secrets Manager Systems Manager (SSM) CloudFront EventBridge SNS SQS CI/CD & DevOps Automation Design and implement end-to-end CI/CD pipelines. Automate application deployments across multiple environments. Implement infrastructure automation and GitOps practices. Build deployment strategies with minimal downtime. Integrate automated testing, security scanning, and quality gates into CI/CD pipelines. Experience with: GitHub Actions Jenkins GitLab CI ArgoCD Infrastructure as Code Develop and manage infrastructure using: Terraform AWS CloudFormation Kubernetes YAML AI & LLM Infrastructure Deploy and manage Small Language Models (SLMs) and Large Language Models (LLMs) in production environments. Build scalable inference infrastructure for AI workloads. Configure GPU-enabled Kubernetes nodes for model serving. Optimize CPU and GPU utilization for AI inference. Manage model deployments, scaling, versioning, and monitoring. Support vector databases and AI inference services. Work closely with AI/ML engineers to optimize model performance and infrastructure costs. Database Infrastructure & Performance Deploy and manage Amazon RDS databases. Monitor and optimize database performance. Implement backup, recovery, and replication strategies. Tune database configurations for high-throughput applications. Monitor slow queries, indexing strategies, and connection pooling. Collaborate with engineering teams on database performance optimization. Monitoring & Observability Implement monitoring and observability using: CloudWatch Prometheus Grafana ELK / OpenSearch Loki Responsibilities include: Infrastructure monitoring Application monitoring Log aggregation Alerting Capacity planning Incident response Security & Compliance Implement AWS security best practices. Design secure IAM policies and access controls. Manage secrets and encryption. Perform infrastructure hardening. Ensure compliance with: SOC 2 HITRUST HIPAA Participate in security audits and vulnerability remediation. Maintain audit logs and infrastructure documentation. Cost Optimization Continuously optimize AWS infrastructure costs. Right-size EC2 instances and EKS node groups. Optimize storage and networking costs. Implement Savings Plans and Reserved Instances where appropriate. Optimize GPU utilization for AI workloads. Monitor cloud spending and recommend cost-saving initiatives. Requirements Required Qualifications Bachelor's or Master's degree in Computer Science, Information Technology, or a related field. 5–8 years of hands-on experience in DevOps, Cloud Engineering, or Platform Engineering. Strong experience designing and managing production AWS environments. Extensive experience with Kubernetes and Amazon EKS. Experience managing enterprise-scale cloud infrastructure. Proven experience automating deployments and infrastructure management. Required Technical Skills Cloud Platforms Amazon Web Services (AWS) AWS Services Amazon EC2 Amazon EKS Amazon ECS Amazon RDS Amazon S3 Lambda ECR CloudFront IAM Route 53 VPC CloudWatch Systems Manager WAF Secrets Manager SNS SQS EventBridge Containers & Orchestration Docker Kubernetes Amazon EKS Helm Kubernetes Networking Ingress Controllers Horizontal & Vertical Pod Autoscaling Infrastructure as Code Terraform CloudFormation Helm Customize CI/CD GitHub Actions Jenkins GitLab CI ArgoCD Databases Amazon RDS PostgreSQL MySQL Redis Experience with: Performance tuning Replication Backup & recovery Connection pooling Query optimization AI Infrastructure Experience deploying and managing: LLMs and SLMs GPU-based inference workloads NVIDIA GPU infrastructure CUDA-enabled environments (preferred) Hugging Face models vLLM, Ollama, or similar inference frameworks Model serving and autoscaling Monitoring & Logging Prometheus Grafana CloudWatch ELK/OpenSearch Loki Security & Compliance Strong understanding of: SOC 2 HITRUST HIPAA IAM RBAC Network Security Encryption Secrets Management Vulnerability Management Preferred Qualifications AWS Certified Solutions Architect – Professional or Associate. AWS Certified DevOps Engineer – Professional. Certified Kubernetes Administrator (CKA) or Certified Kubernetes Application Developer (CKAD). Experience with AI platforms, MLOps, or GPU infrastructure. Experience deploying high-availability, multi-tenant SaaS applications. Familiarity with service mesh technologies (Istio or Linkerd) is a plus.