AI/LLM DevOps Engineer

Job Description – DevOps Engineer – AI/LLM Platform

Location: Gurgaon, Jaipur, Pune, Bhopal, Bangalore, Hyderabad, Chennai

Job Type : Contract 2 hire

Role Overview

We are looking for a skilled DevOps Engineer with hands-on experience in cloud infrastructure, CI/CD, and observability, along with exposure to AI/LLM-based systems. The ideal candidate will be responsible for building and managing scalable infrastructure while enabling reliable deployment and monitoring of modern applications, including AI-driven platforms.

Key Responsibilities

• Design, deploy, and manage scalable cloud infrastructure on AWS, Azure, or GCP
• Develop and maintain Infrastructure as Code (IaC) using Terraform across environments
• Build and manage CI/CD pipelines using GitHub Actions for automated build, test, and deployment
• Implement observability solutions using Prometheus and Grafana for monitoring, alerting, and visualization
• Work with advanced observability tools such as LangFuse for monitoring LLM/AI systems
• Utilize Harness for deployment orchestration, release management, and feature flagging
• Automate operational tasks using Python or Bash scripting
• Monitor system performance, troubleshoot issues, and ensure high availability of production systems
• Collaborate with engineering teams to streamline deployment processes and improve system reliability
• Maintain dashboards, alerts, and runbooks for proactive incident management

Required Skills & Qualifications

• 3–7 years of experience in DevOps / Infrastructure Engineering
• Hands-on experience with at least one cloud platform: AWS, Azure, or GCP
• Strong expertise in Terraform (module creation, state management, multi-environment setup)
• Experience with CI/CD tools, preferably GitHub Actions
• Hands-on experience with Prometheus and Grafana
• Experience in scripting (Python or Bash) for automation
• Understanding of containerization technologies like Docker and Kubernetes
• Strong understanding of system design, networking, and security best practices

Good to Have

• Experience with LLM/AI observability tools such as LangFuse
• Exposure to AI/ML or LLM-based platforms
• Experience with Harness or similar deployment tools