Meet-up group for Big Data professionals and enthusiasts alike where we can share experiences with NoSQL technologies, Distributed Systems, Data Science, Machine Learning, Predictive Analytics - all things Big Data. Come join us and contribute to advancement of this branch of IT in the region.
18:00-18:30 Query pattern in microservice architecture based on event sourcing ( Vladimir Vajda)
18:30-19:00 Journey through the ML model deployment to production (Stanko Kuveljic)
Query pattern in microservice architecture based on event sourcing
Using HTTP as a means of communication between services, introduces tight coupling as each service needs to know about the existence of the other. Event sourcing solves the coupling problem as each service is unaware of any other. It just listens on events of interest, processes them and produces new events. At least, in theory. Even though you have event sourcing, in some cases you cannot avoid asking other service for a piece of information.
This talk is about how to design your services to support the query communication pattern. There are several approaches how this can be solved, none of them is almighty, each has its pros and cons. The decision should be made carefully.
Vladimir Vajda works as Data Engineer at SmartCat. He started as Java developer but got interested in distributed and data intensive systems. Loves great argument, good book, good beer and tasty food. He usually spends his spare time with his family or thinkering and playing with some new technology or project.
Journey through the ML model deployment to production
In this talk, we are going straight into mud dirt and flames. It is not about how to train the ML model, nor how to win a Kaggle competition. It is not about ponies either. Instead, we are going to take a journey through the depths of deployment hell. We will talk about how to bring the ML model to life by exploring several architectures.
The journey will start with a simple Flask application and it will finish with a scalable solution using TensorFlow serving.
Brace yourselves for load tests and performance benchmarks.
Stanko Kuveljic is a data scientist at SmartCat. He graduated master degrees at Faculty of Technical Sciences in Novi Sad with master thesis “The Review of Neural Networks with examples of applications”. He enjoys to work with Spark and Tensorflow. Stanko in few words: Cats, Food, Games, Music, Manga, Anime and FOR THE HORDE!