In this technical deep dive, Seldon’s Andrew Wilson walks through the end-to-end process of integrating MLflow with Seldon Core 2 for robust, production-grade model deployment. Whether you’re a data scientist standardizing on MLflow or an MLOps engineer looking to scale complex model architectures in Kubernetes, this session covers everything from model packaging and deployment to real-time monitoring, pipelines, and drift detection. Includes a full Jupyter notebook demo using scikit-learn and the red wine dataset.
About
Learnings
- Standardized MLflow Integration: Learn how Seldon Core 2 enables seamless deployment of MLflow models using its built-in MLflow runtime, environment packaging, and support for multiple frameworks.
- Flexible Multi-Model Serving: See how Seldon Core’s decoupled server-model architecture optimizes resource use and supports advanced deployments without overprovisioning.
- Data-Centric Pipelines: Explore how Kafka-based pipelines enable chaining of models, preprocessors, postprocessors, and outlier detectors for robust inference workflows.
- Live Deployment Demo: Watch a real-time deployment walkthrough – from training in a local environment to deploying in Kubernetes and running load tests with metrics visualized in Grafana.
- Observability and Optimization: Discover how Seldon offers built-in observability with Prometheus and Grafana, multi-model overcommit strategies, and automated scaling.
- Advanced Use Case: Bonus segment on integrating Alibi Detect to deploy and pipeline a drift detector alongside your model, complete with Kafka output inspection.
Andrew Wilson
Andrew Wilson is the Head of Solutions at Seldon, where he has spent over three years bridging technical innovation and business transformation. With a background in Industrial Engineering, he combines a system-level perspective with a keen eye for user-centric design.
Andrew specializes in leveraging data science, MLOps, and web development to deliver impactful AI-driven solutions. Known for building strong customer relationships, he transforms complex technical challenges into strategic opportunities, helping organizations unlock the full value of their data and AI capabilities.
Complex, real-time use cases is what we do best
Talk with a expert to explore how Seldon can support more streamlined deployments for real-time, complex projects like fraud detection, personalization, and so much more.
MORE RECENT WEBINARS & EVENTS
Stay Ahead in MLOps with our
Monthly Newsletter!
Join over 25,000 MLOps professionals with Seldon’s MLOps Monthly Newsletter. Your source for industry insights, practical tips, and cutting-edge innovations to keep you informed and inspired. You can opt out anytime with just one click.