AIOps - Automating and Scaling ML and LLM Workloads in Production

Learn to deploy AI/ML models in production environments through this conference talk that demonstrates building scalable, secure, and automated pipelines using AIOps principles. Explore an end-to-end architecture utilizing GitLab CI/CD, Terraform, GKE, and FastAPI to automate infrastructure provisioning, containerize applications, and monitor deployed models. Discover how to implement a self-hosted LLM for intelligent Q&A over internal documents using Retrieval-Augmented Generation (RAG) as a practical use case. Master infrastructure automation techniques, deployment best practices, and monitoring strategies essential for taking any AI workload from concept to production-ready implementation using cloud-native tools and methodologies.