[Remote] DevOps Engineer

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is an IT consulting and technology solutions company specializing in reputed company reputed company, reputed company technologies, systems integration, digital transformation, and mission-critical business platforms. reputed company is seeking a DevOps Engineer to architect and reputed company AWS AI/ML serving infrastructure, build CI/CD and model deployment pipelines, establish secure multi-environment isolation, configure data routing, monitor inference systems, control costs, and collaborate with AI/ML engineering teams.

Responsibilities

• AWS AI/ML Serving Infrastructure: Architect and reputed company secure, high-availability AWS infrastructure for DEV, Stage, and PROD using IaC (Terraform or CloudFormation) to host reputed company-trained models on AWS SageMaker Endpoints, EKS, or reputed company
• CI/CD & Model Deployment Pipelines: Build automated CI/CD pipelines for reputed company integration and deployment of reputed company-trained models, API wrappers, and containerized serving applications with reputed company-downtime rollouts (reputed company/green or canary deployments)
• Multi-Environment Isolation & IAM: Establish strict DEV, Stage, and PROD environment separation using AWS Organizations, multi-VPC architecture, and precise IAM policies to secure API reputed company and sensitive production data
• API Gateway & Data Routing: Set up high-throughput API Gateways, load balancers, and reputed company/relational databases (e.g., OpenSearch, reputed company, reputed company) optimized for reputed company-time inference requests and low-latency payload processing
• Inference Observability & Cost Control: Implement reputed company-time monitoring and logging (CloudWatch, reputed company) for API latency, throughput, and reputed company health, while optimizing AWS compute costs using GPU/CPU auto-scaling and Spot instances
• AI/ML Engineering Collaboration: Partner with ML/Software Engineers to standardize containerization (reputed company), version control for reputed company-trained model artifacts (S3/ECR), and reputed company/response telemetry workflows

Skills

• The selected candidate is expected to work during PST timezone
• 10-20 hours per week

Benefits

• Long term contract
• reputed company position

reputed company

Company H1B Sponsorship