Uroš Miletić
IPS, Chief Technology Officer
Prague, Czechia
Actions
Technology leader with strong architecture and development background. Proficient in multiple technologies and platforms. Currently focusing on Microsoft Azure, AI, and cybersecurity.
Previous speaker experiences:
DSC DACH 2024 - https://dscdach.com/speakers/
IPS Open Day 2023 - https://www.linkedin.com/events/workshop-howaicanhelpyoubecomea7100762004520386560
Area of Expertise
Topics
BizTalk to Azure: A practical guide to modernizing integration solutions
With Microsoft BizTalk support ending in 2028, proactive migration planning is essential for a seamless transition. Discover how to leverage cloud technologies to ensure a smooth and efficient migration. Gain insights to future-proof your integration solutions using Azure Logic Apps, Azure Service Bus, Azure API Management, and Azure Integration Services. All information provided is backed by real-world experiences, gained from enterprise customer BizTalk to Azure migration projects.
AI Security for a safer tomorrow
As AI becomes increasingly integrated into our daily lives, ensuring its security is paramount. This talk delves into the critical importance of safeguarding AI systems against emerging threats, such as prompt injection, sensitive information exfiltration, data poisoning, etc. Join to discover how cutting-edge research and cloud-based technologies are shaping a safer tomorrow for AI technologies.
This is a level 200 talk for AI enthusiasts and security specialist. Although some knowledge of GenAI and cybersecurity concepts is welcome, it is not required to enjoy the session.
How we built machining tool wear detection with zero AI know-how
Are you struggling with image classification or object detection, but are intimidated by AI and machine learning?
We used Azure AI Vision and Azure Machine Learning to create a robust image classifier, helping us deliver a machining customer solution for detecting tool wear. This talk will delve into practical demonstrations of using Azure AI services. Attendees will learn how to leverage these powerful platforms to develop and deploy such AI models, without needing an extensive background in data science.
This session is rated at level 200, and is suitable for AI enthusiasts and developers who have a basic understanding of C# and Azure cloud services, but lack specialized knowledge in AI and deep learning. Most parts of the talk will still be interesting, even if attendees have no knowledge of these technologies.
Transition from Azure DevOps to GitHub without CI/CD disruption
Organization made a decision to move from boring old Azure DevOps to new and hip GitHub repositories. Migration must be done as soon as possible, without jeopardizing delivery. What to do?!
This session, inspired by a real-world micro-service application migration, will teach you step-by-step strategies and best practices to ensure a seamless transition from Azure DevOps to GitHub. By the end of the talk, you will have a clear understanding of how to manage repository migrations smoothly and securely, while maintaining operational efficiency.
This level 200 talk is tailored for DevOps enthusiasts who are eager to deepen their understanding of Git repository and CI/CD migration. While the session is designed with a technical audience in mind, even those with little to no prior knowledge of Azure DevOps or GitHub will find the content accessible and engaging.
ChatGPT under the hood
Ever wanted to peek behind the curtain of ChatGPT? It might have been a single LLM answering your prompts in its inception, but today it is a rather complex system using state-of-the art GenAI technologies.
In this session, we'll take you on a journey through the overall architecture of agentic systems and how they power applications like ChatGPT. We'll uncover the key components and design principles that make these systems tick. From orchestrating natural language processing capabilities to integrating various subsystems, this talk will provide a comprehensive overview of the techniques and best practices for building advanced conversational agents.
This talk is rated at level 300. It is perfect for AI practitioners and developers with a solid grasp of software architecture concepts and LLMs, who are eager to deepen their understanding of agents and agentic systems. The concepts presented are abstract and not dependent on any specific technology, making this presentation interesting for non-technical professionals as well.
Microsoft Copilot under the hood
Ever wanted to peek behind the curtain of Microsoft Copilot? It might have been a single LLM answering your prompts in its inception, but today it is a rather complex system using state-of-the art GenAI technologies.
In this session, we'll take you on a journey through the overall architecture of agentic systems and how they power applications like Microsoft Copilot. We'll uncover the key components and design principles that make these systems tick. From orchestrating natural language processing capabilities to integrating various subsystems, this talk will provide a comprehensive overview of the techniques and best practices for building advanced conversational agents.
This talk is rated at level 300. It is perfect for AI practitioners and developers with a solid grasp of software architecture concepts and LLMs, who are eager to deepen their understanding of agents and agentic systems. The concepts presented are abstract and not dependent on any specific technology, making this presentation interesting for non-technical professionals as well.
Common pitfalls in developing generative AI applications
Curious about the challenges that can arise when developing generative AI applications? While such technologies offer incredible potential, they also come with their own unique set of hurdles.
In this session, we'll explore the common pitfalls encountered during the development of generative AI applications. We will discuss the appropriate contexts for using generative AI solutions, how to avoid jumping into complex solutions prematurely, and why keeping human in the loop is essential for success. By examining real-world examples, we'll highlight the mistakes to avoid and the best practices to follow to ensure your generative AI projects have successful outcome.
This talk is rated at level 200. It is ideal for AI practitioners and developers with a solid understanding of AI concepts. The insights shared will be valuable for both technical and non-technical professionals interested in the practical aspects of generative AI development.
move(data) 2025 Sessionize Event Upcoming
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top