Job Description - AI DevOps Engineer (LLM)

Job Title: AI DevOps Engineer (LLM)
Experience:3 - 7 Years
Location:Bengaluru

Job Summary

We are seeking an experienced AI DevOps Engineer with strong expertise in deploying automating and managing Large Language Model (LLM) applications in production environments. The ideal candidate must have hands-on experience with LLMs and should have successfully delivered real-world AI/GenAI implementations (not just Proof of Concepts).

The candidate should possess strong DevOps expertise with CI/CD pipelines cloud platforms containerization and MLOps practices to enable scalable secure and reliable AI deployments.

Key Responsibilities

• Design implement and manage production-grade AI/LLM infrastructure and deployment pipelines.
• Deploy and maintain Large Language Model (LLM) applications in production environments.
• Build and optimize CI/CD pipelines for AI/ML workloads.
• Collaborate with AI/ML Engineers Data Scientists and Software Engineers to deploy and monitor AI solutions.
• Automate model deployment versioning rollback and monitoring.
• Manage containerized applications using Docker and Kubernetes.
• Configure Infrastructure as Code (IaC) using Terraform or similar tools.
• Implement monitoring logging alerting and observability for AI applications.
• Optimize AI infrastructure for scalability reliability security and cost.
• Ensure governance security and compliance for AI deployments.

Required Skills

• 3 years of experience in DevOps Cloud or Platform Engineering.
• Mandatory hands-on experience with Large Language Models (LLMs).
• Must have delivered production-ready AI/GenAI implementations (POC experience alone is not sufficient).
• Strong experience with CI/CD pipelines using Jenkins GitHub Actions GitLab CI or Azure DevOps.
• Experience with Docker and Kubernetes.
• Strong knowledge of AWS Azure or GCP.
• Experience with Infrastructure as Code (Terraform CloudFormation or ARM Templates).
• Experience with monitoring and observability tools such as Prometheus Grafana ELK Datadog or CloudWatch.
• Strong scripting skills in Python Bash or PowerShell.
• Experience with Git and version control best practices.

Required Skills:

AIArtificial IntelligenceDevOpsLLMLangchainlangraphCI/CD