DevOps Engineer – AI/ML Infrastructure & MLOps

About Practicus AI

Practicus AI is a next-generation Data Intelligence and Generative AI platform that enables organizations to rapidly deploy, monitor, and govern AI/ML models, including cutting-edge large language models (LLMs). Built cloud-native and fully containerized, our platform empowers secure, scalable AI innovation for enterprises around the world.

About the Role

We’re hiring a DevOps Engineer with hands-on Kubernetes experience and a deep interest in MLOps and LLMOps. You’ll play a central role in helping us deploy and manage scalable infrastructure for AI workloads across Kubernetes and OpenShift clusters. From model training environments to LLM inference servers, your work will help operationalize the next generation of AI capabilities.

This role is ideal for someone who thrives in a fast-paced, open-source-first environment, and is excited to work alongside data scientists, platform engineers, and AI researchers to build robust DevOps and MLOps pipelines.

What You’ll Do

• Build and operate Kubernetes and OpenShift clusters to support containerized AI/ML and LLM workloads.
• Support deployment of LLMs and other models.
• Design and maintain CI/CD pipelines for automated model and service deployment.
• Create Docker container images optimized for Python-based data and AI services.
• Ensure secure, observable, and resilient AI/ML infrastructure, including SSO, LDAP, secrets, and service-to-service authentication.
• Integrate monitoring, logging, and alerting tools (Grafana, Prometheus, Fluent Bit) to enable model observability and infrastructure insight.
• Work closely with AI engineers and MLOps teams to manage data pipelines, GPU resources, and containerized model inference services.

What We’re Looking For

• Experience managing Kubernetes clusters (AKS, GKE, EKS, or OpenShift).
• Hands-on experience with container orchestration, Docker image creation, and YAML-based Kubernetes configuration.
• Linux administration and shell scripting skills.
• Familiarity with cloud-native deployment best practices, RBAC, service mesh (e.g., Istio), and secure ingress.

Bonus experiences:

• Deploying and serving AI/ML models in production environments.
• Exposure to large language model hosting, inference pipelines, and MLOps tools like MLflow or Airflow.
• Experience with GPU-based model inference at scale.

Why Join Practicus AI?

At Practicus AI, you’ll help build the infrastructure behind the future of AI. You’ll contribute to a secure, open, and modular AI platform used by data scientists and engineers across the world. If you're passionate about DevOps and want to work at the edge of AI innovation—this is your opportunity.