In this technical deep dive, explore the full lifecycle of deploying and monitoring machine learning models in production using Seldon on Kubernetes. The session uses a computer vision use case – from training a PyTorch model to deploying it with Seldon Core 2 and monitoring it with Prometheus and Grafana. Viewers also learn how to implement drift detection, payload logging, and custom runtime logic. Whether you’re building out your first production system or scaling a fleet of models, this webinar offers actionable insight into efficient, scalable, and observable model serving with open technologies.
About
Learnings
-
Serving models at scale with Seldon Core: Understand the difference between Core V1 and V2, and how to serve PyTorch models using MLServer or NVIDIA Triton on Kubernetes with flexible, modular infrastructure.
-
Model orchestration, ensembles, and pipelines: Learn how to chain models, preprocessors, and detectors into dynamic pipelines with synchronous and asynchronous processing for production-ready deployment.
-
Drift detection with Alibi Detect: See how to implement input or output drift detectors that alert you to model degradation in the absence of ground truth labels.
-
Monitoring and logging for compliance and performance: Explore how Prometheus and Grafana (and optionally Datadog) enable real-time visibility into throughput, latency, memory, and custom model metrics.
-
Best practices for real-world deployment: Gain insight into memory management with overcommit, payload logging with Kafka, using open inference protocol, custom wrapper design, and version control strategies for models in production.
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.