Role : AI DevOps Engineer
Experience : 5 9 years
Qualification : Bachelors degree in computer science, computer engineering, IT, Data Science
Location : Pune or Remote India only
Role Overview
We are seeking a skilled and proactive AI DevOps Engineer to design, implement, and manage scalable infrastructure and deployment pipelines for AI-driven applications.
The ideal candidate will have strong expertise in Kubernetes, cloud platforms, and CI/CD practices, along with hands-on experience in managing LLM-based workloads and GPU-enabled environments.
Key Responsibilities
- Design, deploy, and manage highly available and scalable infrastructure for AI/ML applications.
- Build and maintain Kubernetes clusters (EKS/OKE) with a focus on performance, scalability, and reliability.
- Develop and manage Helm charts, ingress controllers, and optimize networking configurations.
- Implement and manage CI/CD pipelines using Jenkins, ArgoCD, and GitOps methodologies.
- Deploy and manage LLM serving frameworks such as vLLM, Ollama, and Open WebUI.
- Optimize GPU resource allocation and utilization in containerized environments.
- Automate infrastructure provisioning using Terraform and manage cloud-native services.
- Integrate security best practices into DevOps workflows, including automated vulnerability scanning and remediation.
- Monitor system performance and reliability using Prometheus, Grafana, Loki, and Alertmanager.
- Collaborate with development and AI teams to build developer-friendly automation tools and workflows.
Required Skills & Qualifications
- Deep expertise in Kubernetes (EKS/OKE) including cluster management, networking, and scaling.
- Strong experience with CI/CD tools such as Jenkins and ArgoCD.
- Proficiency in AWS (mandatory); experience with OCI is a plus.
- Hands-on experience with Infrastructure as Code tools like Terraform.
- Experience in deploying and managing LLM-based systems (vLLM, Ollama, Open WebUI).
- Strong understanding of containerization and orchestration (Docker, Kubernetes).
- Experience with monitoring and logging tools like Prometheus, Grafana, Loki.
- Solid understanding of security practices including vulnerability management tools like Veracode and Trivy
(ref:hirist.tech)
