Cloud-Native MLOps Platform for Python- and ML Engineers
summary
Company with ~50 people and 3+ years of history presents a cloud-native stack that moves Python ML code from local POC to Kubernetes with concrete pieces: DocArray for typed multimodal documents and pluggable vector DB backends, Jina MLOps executors/flows exposing gRPC and HTTP with built-in OpenTelemetry metrics/traces, and jcloud operator that adds autoscaling, GPU allocation and DNS so flows deploy to k8s as real services — demos include encoder+indexer search and text→image generation.
AI-written summary · about
chapters (16)
- 0:00Introduction
- 1:04Presentation outline
- 3:31Deep learning use cases
- 5:19ML deployment challenges
- 6:21Dockery for local POCs
- 9:08Dockery components
- 11:35Building POC with Dockery
- 15:28Serving models with Gina
- 17:56Orchestrating executors with Gina
- 19:24Adding observability with Gina
- 21:32Cloud deployment with Kubernetes
- 23:17Kubernetes for ML workloads
- 25:46Gina and Kubernetes integration
- 26:51Simplifying deployments with JCloud
- 27:54Summary
- 28:50Q&A
related talks
35mCloud-Native MLOps Platform for Python- and ML Engineers
36mAccessible Neural Search and Cloud-Nativeness for ML Engineers
36mDataOps and MLOps: NLP Development and Deployment in Kubernetes made easy
22mBuilding a MLOps Platform with Kubeflow on GKE
53mExperience with an end-to-end MLOps pipeline: Practical insights and 3D architectural perspectives
29mTeam Teardown: MLOps in the Cloud for IoT
31mProductionizing ML with ML Ops and Cloud AI
33mBuilding & Managing MLOps Pipelines in the Cloud