AI DevOps Engineer (AI Platform & LMS)

Chandigarh University; Mohali; On-site; INR 1,800,000 - 2,600,000; Full time

Job summary

Chandigarh University, Mohali, Punjab, invites an AI DevOps Engineer to join the AI Platform & LMS team. You will build CI/CD pipelines for AI, RAG, API and LMS applications with automated testing, Docker builds, security checks and rollback capabilities.

You will deploy and optimize LLMs on AWS/on-prem GPUs, manage CUDA environments and costs, containerize services with Docker, and run Kubernetes/EKS. You will own Moodle/CULMS deployments, upgrades, patches, and plugin lifecycle, plus CUIMS/ERP

Qualifications

• Hands-on experience with LLM deployment, RAG and model-serving.
• Strong AWS, Linux, Docker and Kubernetes expertise.
• Proficient in Git and CI/CD toolchains, with scripting in Python/Bash.

Responsibilities

• Build CI/CD pipelines for AI, RAG, API and LMS applications with automated testing and security checks.
• Deploy and optimize LLMs on AWS/on-prem GPUs, manage CUDA environments and costs.
• Containerize services with Docker and run on Kubernetes/EKS, including ingress and storage.
• Own Moodle/CULMS deployments, upgrades, patches and plugin lifecycle, plus CUIMS/ERP, SSO and LTI integrations.
• Monitor platforms with Prometheus, Grafana, and CloudWatch; handle incidents and DR.
• Enforce security (IAM, secrets, TLS) and maintain change documentation.

Skills

AWS

Linux

Docker

Kubernetes

Git

CI/CD

Python scripting

Bash scripting

Education

B.Tech/M.Tech in CS/IT/AI/Data Science or MCA

Tools

Terraform

Job description

Position: AI DevOps Engineer (AI Platform & LMS)

Location: Mohali, Punjab

• Build CI/CD pipelines for AI, RAG, API and LMS applications, with automated testing, Docker builds, security checks and rollback; manage GitOps and IaC (Terraform/Ansible/Helm).
• Deploy and optimize LLMs (Llama, Qwen, Mistral, Gemma) via vLLM, Ollama or Hugging Face on AWS/on-premise GPUs, managing CUDA environments, performance and cost.
• Deploy RAG pipelines and vector databases (Qdrant, Milvus, Weaviate, pgvector) along with Python/FastAPI AI services.
• Manage AWS (EC2/GPU, EKS, ECR, S3, VPC, IAM, CloudWatch), hybrid connectivity, backup, recovery, scaling and cost optimization.
• Containerize services with Docker and run them on Kubernetes/EKS, including ingress, secrets, storage, scaling and troubleshooting.
• Own Moodle/CULMS deployments, upgrades, patches and the plugin lifecycle (compatibility, security, UAT, release), plus cron, caching, backups and CUIMS/ERP, SSO and LTI integrations.
• Monitor platforms with Prometheus, Grafana and CloudWatch; handle incidents, root-cause analysis and disaster recovery.
• Enforce security (IAM, secrets, TLS, least privilege, patching), protect institutional data and maintain change documentation.

Qualifications

• B.Tech or M.Tech in CS, IT, AI or Data Science, or MCA.
• 37 years in DevOps, Cloud, MLOps, AI Infrastructure or related roles.
• Hands-on LLM deployment, RAG and model-serving experience.
• Strong AWS, Linux, Docker, Kubernetes, Git and CI/CD skills; Python and Bash scripting.
• Preferred: Moodle/CULMS deployment, upgrade or plugin experience, and AWS, CKA, CKAD or Terraform certifica