Description:

Rethem is seeking a hands-on Agentic AI Ops Engineer who excels at the intersection of cloud infrastructure, AI agent systems, and DevOps automation.
The role involves building and maintaining the CI/CD infrastructure for Agentic AI solutions using Terraform on AWS.
Responsibilities include designing, implementing, and maintaining CI/CD pipelines for Agentic AI applications, automating deployment of multi-agent systems, and collaborating with ML/NLP engineers to develop and deploy AI agents.
The engineer will implement end-to-end observability for agents, design dashboards for monitoring performance, and manage cost metrics associated with agentic operations.
The position requires collaboration with product, backend, and AI teams to improve agentic infrastructure design and tool orchestration workflows.

Requirements:

Candidates must have 2+ years of experience in DevOps, MLOps, or Cloud Infrastructure with exposure to AI/ML systems.
Deep expertise in AWS serverless architecture is required, including hands-on experience with AWS Lambda, Amazon API Gateway, Step Functions, S3, DynamoDB, EventBridge, and SQS.
Strong proficiency in Terraform for building and managing serverless AWS environments is essential.
Experience in deploying and managing CI/CD pipelines for serverless and agent-based applications using AWS CodePipeline, CodeBuild, CodeDeploy, or GitHub Actions is necessary.
Candidates should have hands-on experience with agent and tool development in Python, including debugging and performance tuning.
A solid understanding of IAM roles and policies, VPC configuration, and least-privilege access control is required.
Deep understanding of monitoring, alerting, and distributed tracing systems is essential.
Excellent debugging, documentation, and cross-team communication skills are necessary.