DevOps Engineer

Job Title: DevOps Engineer – AI/ML Infrastructure

Location: Meril Healthcare Pvt. Ltd, IITM research park, Chennai, Parent company – Meril (https://www.merillife.com/) .

Shift: General shift - Monday to Saturday (9.30 am to 6.00 pm).

Summary

We are seeking a skilled DevOps Engineer with expertise in managing cloud-based AI/ML infrastructure, automation, CI/CD pipelines, and containerized deployments. The ideal candidate will work on AWS-based AI model deployment, database management, API integrations, and scalable infrastructure for AI inference workloads. Experience in ML model serving (MLflow, TensorFlow Serving, Triton Inference Server, BentoML) and on- prem/cloud DevOps will be highly valued.

Key Responsibilities

Cloud s Infrastructure Management

• Manage and optimize cloud infrastructure on AWS (SageMaker, EC2, Lambda, RDS, DynamoDB, S3, CloudFormation).
• Design, implement, and maintain highly available, scalable AI/ML model deployment pipelines.
• Set up Infrastructure as Code (IaC) using Terraform, CloudFormation, or Ansible.

CI/CD s Automation

• Develop and manageCI/CD pipelines using GitLabCI/CD, Jenkins, and AWS CodeBuild.
• Automate deployment of AI models and applications using Docker, Kubernetes (EKS).
• Write automation scripts in Bash, Python, or PowerShell for system tasks.

APIs AI Model Deployment

• Deploy and manage Flask/FastAPI-based APIs for AI inference.
• Optimize ML model serving using MLflow, TensorFlow Serving, Triton Inference Server, and BentoML.
• Implement monitoring for AI workloads to ensure inference reliability and performance.

Security, Monitoring s Logging

• Implement AWS security best practices (IAM, VPC,Security Groups, Access Controls).
• Monitor infrastructure using Prometheus, Grafana, CloudWatch, or ELK Stack.
• Set up backup and disaster recovery strategies for databases, storage, and models.

Database s Storage Management

• Maintain and optimize MySQL (RDS) and MongoDB (DynamoDB) databases.
• Handle structured (RDS) and unstructured (S3, DynamoDB) AI data storage.
• Improve data synchronization between AI models, applications, and web services.

On-Prem s Hybrid Cloud Integration (Optional)

• Manage on-prem AI workloads with GPU acceleration.
• Optimize AI workloads across cloud and edge devices.

Required Skills and Qualifications

• 3 to 5 years of experience in DevOps, Cloud Infrastructure, or AI/ML Ops.
• Expertise in AWS (SageMaker, EC2, Lambda, RDS, DynamoDB, S3).
• Experience with Docker s Kubernetes (EKS) for container orchestration.
• Proficiency in CI/CD tools (Jenkins, GitLab CI/CD, AWS CodeBuild).
• Strong scripting skills in Bash, Python, or PowerShell.
• Knowledge of Linux ecosystem (Ubuntu, RHEL, CentOS).

• Hands-on experience with ML model deployment (MLflow, TensorFlow Serving, Triton, BentoML).
• Strong understanding of networking, security, and monitoring.
• Experience with database management (MySQL, PostgreSQL, MongoDB).

Preferred Skills

• AWS Certified DevOps Engineer, CKA (Kubernetes), or Terraform certification.
• Experience with hybrid cloud (AWS + on-prem GPU servers).
• Knowledge of edge AI deployment and real-time AI inference optimization.

Interested , Please share your resume to [email protected]