Declarative MLOps - Streamlining Model Serving on Kubernetes

Name: Declarative MLOps - Streamlining Model Serving on Kubernetes
Uploaded: 2023-04-18

Posted Apr 18, 2023 | Views 514

# Declarative MLOps

# Streamlining Model Serving

# Kubernetes

SPEAKER

Rahul Parundekar

Founder @ A.I. Hero, Inc.

Rahul has 13+ years of experience building AI solutions and leading teams. He is passionate about building Artificial Intelligence (A.I.) solutions for improving the Human Experience. He is currently the founder of A.I. Hero - a platform that helps you train ML models and help improve data quality declaratively. As part of his work, he also helps companies bring LLM Models into production by working on an end-to-end LLM Ops Stack on top of Kubernetes that helps you keep your fine-tuning, data annotation, chat-bot deployment, and other LLM operations in your own VPC.

+ Read More

SUMMARY

Data Scientists prefer Jupyter Notebooks to experiment and train ML models. Serving these models in production can benefit from a more streamlined approach that can guarantee a repeatable, scalable, and high velocity. Kubernetes provides such an environment. And while third-party solutions for serving models make it easier, this talk demystifies how native K8s operators can be used to deploy models along with best practices for containerizing your own model, and CI/CD using GitOps.

+ Read More