Description

Design and operate AI-ready cloud platforms with a focus on infrastructure architecture, cost governance, and LLMOps.

This role is remote.

Responsibilities

• Architect shared AI platforms using Kubernetes (EKS/AKS), container orchestration, and serverless components.
• Implement infrastructure-as-code (Terraform, Bicep, CloudFormation) for automated provisioning and environment standardization.
• Manage LLMOps workflows including model lifecycle, versioning, rollout strategies, and operational governance for large language models.
• Configure cloud-native networking, hybrid connectivity, VPN/Direct Connect, and private endpoints.
• Enforce cost governance for AI platforms through usage metering, quota management, and inference cost optimization.

Required Skills

• 8-15 years of experience in cloud infrastructure architecture.
• Deep expertise in compute, networking, storage, IAM, security, and observability.
• Proficiency with Amazon Bedrock and Azure AI Foundry, including tenant isolation and enterprise-scale deployment.
• Strong LLMOps experience covering model versioning, prompt management, and monitoring.
• Hands-on experience with Kubernetes (EKS/AKS) and distributed systems.
• Knowledge of cloud-native networking and hybrid connectivity solutions.
• Bachelor of Computer Science degree.

Preferred Skills

• Experience with Bicep for infrastructure management.
• Background in building and operating shared AI platforms.

Refer and earn ₹50,000! World's #1 IT Specific Global Technology Job Portal

Key Skills

Education

Bachelor of computer science