Job Description

Roles & Responsibilities

• 1. Infrastructure Support & Environment Management
  • Set up and maintain compute infrastructure, including GPU-enabled environments.
  • Configure and manage Linux-based systems for development and production environments.
  • Provisioning and configuration of cloud and on-prem infrastructure.
  • Monitor system resources and assist in performance tuning and optimization.
• 2. Containerization & Deployment
  • Build and manage containerized applications using Docker.
  • Deploy and manage applications on Kubernetes clusters under guidance from senior engineers.
  • Creating deployment configurations, Helm charts, and environment setups.
  • Support scaling and orchestration of microservices and AI workloads.
• 3. CI/CD Pipeline Implementation
  • Develop and maintain CI/CD pipelines for application and AI model deployment.
  • Automate build, test, and deployment processes using tools like Azure DevOps, GitHub Actions, or Jenkins.
  • Ensure smooth promotion of code and models across environments (dev, test, prod).
  • Troubleshoot pipeline failures and deployment issues.
• 4. MLOps & AI Deployment Support
  • Deploying machine learning models and LLM-based services.
  • Integration of AI components into production systems.
  • Contribute to model versioning, monitoring, and lifecycle management.
  • Work with AI engineers to operationalize RAG pipelines and inference services.
• 5. Monitoring, Logging & Issue Resolution
  • Implement and maintain monitoring and logging solutions (e.g., Prometheus, Grafana, ELK).
  • Track application performance, system health, and availability.
  • Respond to incidents, troubleshoot issues, and escalate when required.
  • Assist in root cause analysis and continuous improvement.
• 6. Automation & Scripting
  • Write scripts (Python, Bash) to automate repetitive operational tasks.
  • Support Infrastructure as Code (IaC) initiatives using tools like Terraform or ARM templates.
  • Improve operational efficiency through automation and tooling.
• 7. Collaboration & Support
  • Work closely with Senior DevOps/MLOps Engineers, AI Engineers, and Development teams.
  • Support developers in environment setup, debugging, and deployment processes.
  • Follow DevOps and MLOps best practices and continuously improve operational workflows.

Desired Candidate Profile

• Bachelor’s degree in Computer Science, Engineering, or related field.
• 7+ years of experience in DevOps or platform engineering roles.
• Basic to intermediate experience with Linux system administration.
• Hands-on experience with Docker and containerization.
• Familiarity with Kubernetes (deployment and basic management).
• Experience with CI/CD tools (Azure DevOps, GitHub Actions, Jenkins, etc.).
• Basic understanding of cloud platforms (Azure, AWS, or GCP).
• Scripting skills in Python, Bash, or similar.
• Understanding of version control systems (Git).

Preferred Skills

• Exposure to AI/ML model deployment and MLOps practices.
• Familiarity with LLM deployment concepts and tools.
• Basic knowledge of GPU environments and high-performance computing.
• Experience with monitoring and logging tools (Prometheus, Grafana, ELK).
• Knowledge of Infrastructure as Code (Terraform, ARM templates).
• Understanding of microservices architecture.

Key Performance Indicators (KPIs)

• Deployment success rate and pipeline stability.
• System uptime and availability.
• Resolution time for incidents and issues.
• Efficiency of CI/CD processes.
• Infrastructure utilization and basic cost optimization.
• Support effectiveness for development and AI teams.

Stakeholders & Reporting

• Reports to: Senior DevOps / MLOps Engineer / Platform Lead
• Key Stakeholders:
  • AI Engineers & Data Scientists
  • Backend & Frontend Developers
  • DevOps / Platform Team
  • QA & Release Management Teams