CO-LOCATED EVENTS

Hotel Metropol, Belgrade

18th-22nd November 2024

DSC Europe 24 SCHEDULE

Schedule for day 2 is coming soon

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut elit tellus, luctus nec ullamcorper mattis, pulvinar dapibus leo.

Stream 1

TRANSFORMING
INDUSTRIES WITH AI,
GENERATIVE AI

Mastering RAG Evaluation with MLflow and Open Source LLMs in Nebius AI-Studio

Technical Tutorial, Educational Tutorial
Beginner to Intermediate
This hands-on tutorial will guide participants through the comprehensive evaluation of Retrieval-Augmented Generation (RAG) pipelines using MLflow and open source LLM models. Attendees will learn to implement and track sophisticated LLM-specific metrics, optimize RAG systems and manage experiments efficiently. The tutorial covers setting up MLflow, creating custom metrics, evaluating different building blocks of RAG pipelines and visualizing results.
10:00

 –

11:30

Mastering RAG Evaluation with MLflow and Open Source LLMs in Nebius AI-Studio

Cyril Kondratenko & Mikhail Rozhkov
Solutions Architect @ Nebius & Technical Product Manager @ Nebius

Building Data Breach Search Engines with MariaDB

Tech tutorials
Intermediate
MariaDB is an interesting, but a very complex beast. This workshop will walk you through the ins and outs of data breach search engines and other big data applications based on MariaDB allowing you to understand how, why, and when MySQL and MariaDB works the way it does.
11:45

 –

13:15

Building Data Breach Search Engines with MariaDB

Lukas Vileikis
Founder @ BreachDirectory.com

Unlocking Personalization: A Deep Dive into Modern Recommendation Algorithms

Technical Tutorial
Intermediate
This comprehensive tutorial takes participants on a journey through the fascinating evolution of recommendation systems, exploring the cutting-edge techniques that power today’s most sophisticated recommender engines. From simple heuristics to advanced deep learning models, attendees will gain hands-on experience with a wide range of algorithms and methodologies.
The tutorial is structured to cover the following key areas:
Foundational Heuristics: Understanding basic recommendation techniques
Collaborative Filtering: Exploring user-based and item-based approaches
Two-Tower Neural Networks: Diving into deep learning for recommendations
Large Language Models (LLMs): Harnessing the power of transformers for personalized suggestions
Participants will work with real-world datasets, implementing and comparing various recommendation algorithms using popular libraries and packages. By the end of the tutorial, attendees will have a solid understanding of the entire recommendation system pipeline, from data preprocessing to model deployment.
This hands-on session is designed for data scientists, machine learning engineers, and researchers interested in building state-of-the-art recommendation systems. Participants should have a basic understanding of Python programming and machine learning concepts.
Join us for an immersive experience that will equip you with the knowledge and skills to create powerful, personalized recommendation systems for a variety of applications.
13:30

 –

15:00

Unlocking Personalization: A Deep Dive into Modern Recommendation Algorithms

Sarang Gupta
Lead Data Scientist, Machine Learning @ Asana

Solutions prototyping using Azure AI Studio

Technical Tutorial
Beginner to Intermediate
During the tutorial we will explore the capabilities of this Azure AI Studio. This session is designed for developers eager to harness the potential of this platform for rapid AI prototyping and deployment. We will begin by examining the platform’s core features and the diverse range of available models. The tutorial will include hands-on demonstrations of quick prototyping projects, such as creating a chatbot using your own data, generating images, recognizing the status of electricity meters, and describing pictures. By the end of this session, participants will have a solid understanding of how to leverage Azure AI Studio to assess the potential of the planned AI solutions.
15:15

 –

16:45

Solutions prototyping using Azure AI Studio

Pawel Ekk-Cierniakowski
Data Science Domain Lead @ SoftwareOne

Stream 2

TRANSFORMING
INDUSTRIES WITH AI,
GENERATIVE AI

How to build AI Agents: A step by step guide to creating AI agents

Technical Tutorial
Beginner to Intermediate
In today’s rapidly evolving technological landscape, AI agents are transforming from buzzwords into practical tools that can automate tasks, make decisions, and augment human capabilities. Yet, for many developers and tech enthusiasts, creating AI agents remains a mysterious black box. This talk demystifies the process, offering a practical, hands-on guide to building functional AI agents from scratch.

I will walk you through the fundamental components of an AI agent, demonstrating how to combine modern language models, tools, and frameworks to create purposeful agents. We’ll start with a simple agent that can complete basic tasks and progressively enhance it to handle complex workflows.

Key takeaways will include:

– What are AI Agent and why do they matter
– Components andTools required to build AI agents
– Understanding the core architecture of AI agents
– Best practices for building and deploying agents

This session will equip you with the knowledge and tools to start building your own AI agents today.

Target Audience: Developers, technical product managers, and technology enthusiasts with basic programming knowledge. No prior AI experience required.
10:00

 –

11:30

How to build AI Agents: A step by step guide to creating AI agents

John Robert
Senior ML Engineer and Founder of “Don’t Fear AI”

Automation of the Automation using GenAI

Technical Tutorial
Intermediate
Tired of boring automation of page objects, locators, and smoke tests for yet another REST API service? Or do you want to automatically update your tests each time a new change happens? Join us to explore practical applications of GenAI in automating the creation of such tests. This talk will cover the creation of a framework that integrates code generation with self-healing capabilities. Learn how to streamline repetitive QA tasks, improve test coverage, and handle common issues when GenAI falls short. Gain insights into the benefits and limitations of using AI to enhance QA automation efficiency and reliability.
11:45

 –

13:15

Automation of the Automation using GenAI

Gennadi Chursov
Lead SDET @ Serbian QA Hub

From Walruses to Code: A Guide to Tackling Unique ML Problems

Technical Tutorial, Educational Tutorial
Beginner to Intermediate
At the tutorial, we will analyze the specifics of choosing a technology for solving non-standard tasks and how to get a result with a small dataset
13:30

 –

15:00

From Walruses to Code: A Guide to Tackling Unique ML Problems

Dmitrii Solomonov
team lead b2b team backend @ yandex 360

Introduction to orchestration ETL processes with Apache Airflow

Technical Tutorial
Beginner to Intermediate
The aim of this tutorial is to demonstrate the usage of Apache Airflow to orchestrate ETL processes. Apache Airflow is an open-source workflow management platform for data engineering pipelines. In this tutorial a brief overview of architecture will be shown as well as core concepts of Apache Airflow such as DAGs, Tasks, Variables, Params and XComs. These concepts will be demonstrated through examples of ETL processes that are easily understandable and represent a good foundation to start to work with Apache Airflow. It is required to have some basic knowledge of Python programming language, running Docker containers and SQL language.
15:15

 –

16:45

Introduction to orchestration ETL processes with Apache Airflow

Miroslav Tomic
Teaching Assistant @ University of Novi Sad, Faculty of Technical Sciences

Stream 3

TRANSFORMING
INDUSTRIES WITH AI,
GENERATIVE AI

Data Engineering in the AI Era: Building a Robust Foundation for AI Applications

Technical Tutorial
Data is the foundational layer for any AI application. In this talk, we will explore Wheely’s evolution in building robust data pipelines and employing advanced data modeling techniques:

— Enabling Data Streaming: Transitioning to near real-time and event-driven applications using Debezium and Snowplow.
— Reducing third-party vendor dependencies by leveraging open-source software, resulting in annual savings of $20K.
— Achieving full control over data flow and transformations using dbt and Kafka SMT.
— Optimizing compute and storage costs with Snowflake, achieving a 30% reduction compared to Amazon Redshift.
— Ensuring complete data ownership with zero processing outside the company perimeter.
— Securing data access through RBAC, data masking policies, and PII handling.
— This talk distills key knowledge, revealing multiple challenges and pitfalls, and provides practical insights for building a solid data foundation for AI applications.
10:00

 –

11:30

Data Engineering in the AI Era: Building a Robust Foundation for AI Applications

Artemiy Kozyr
Data Architect @ Independent Consultant

Building Multiagent Systems: An Ontology-Driven Approach with SPADE

Technical Tutorial, Research Tutorial, Educational Tutorial
Intermediate
In this online tutorial, we’ll explore how to efficiently model and implement multiagent systems using an ontology-driven approach. We’ll start by introducing a specific ontology designed to represent the structure and behaviour of agents within a system. From there, we shall demonstrate how to translate this conceptual model into a functional implementation template using the SPADE (Smart Python Agent Development Environment) platform. By the end of the session, you’ll have a clear understanding of how to move from theory to practice, streamlining the development process for complex multiagent systems. This hands-on tutorial is ideal for developers and researchers looking to enhance their agent-based system design skills.
11:45

 –

13:15

Building Multiagent Systems: An Ontology-Driven Approach with SPADE

Bogdan Okresa Djuric
Associate Professor @ University of Zagreb, Faculty of Organization and Informatics, Artificial Intelligence Laboratory

Stream 4

TRANSFORMING
INDUSTRIES WITH AI,
GENERATIVE AI

stream 5

TRANSFORMING
INDUSTRIES WITH AI,
GENERATIVE AI

stream 6

TRANSFORMING
INDUSTRIES WITH AI,
GENERATIVE AI

* this program is not final and is subject to chance, full schedule will be available soon