Alex Shershebnev
Head of ML/DevOps at Zencoder
Funchal, Portugal
Actions
Alex Shershebnev is a seasoned Computer Vision and MLOps Engineer with over ten years of experience shaping the future of AI-driven software development. Currently, Alex leads the ML/DevOps team at Zencoder, where he leverages his extensive background in Software Engineering, ML and DevOps to deliver high-quality machine learning solutions. His work spans complex data pipelines, cloud infrastructure management (GCP, Kubernetes), and advanced ML/DevOps pipelines, ensuring scalability and efficiency. Before Zencoder, Alex played pivotal roles in numerous projects, including leading teams at Sanas, ivi and MTS AI. His technical expertise in machine learning, data science, and bioinformatics has led to impactful solutions across industries, ranging from bioinformatics at the University of Massachusetts to video analysis at ivi.ru and MTS AI. Alex has a proven track record of managing complex infrastructure that scales to hundreds of GPUs, enabling effective and easy use of cloud infrastructure for data scientists while driving down costs through cloud consolidation efforts and boosting productivity through the deployment of sophisticated AI models. In addition to his technical contributions, Alex has been instrumental in mentoring teams and fostering a culture of innovation and collaboration. His deep understanding of AI systems, from developing recommendation engines to cutting-edge computer vision algorithms to voice and NLP, positions him as a thought leader in the AI and ML space. Whether it’s speaking on the latest advancements in MLOps, sharing insights on AI-driven automation, or discussing the future of AI in the enterprise, Alex brings a wealth of knowledge, practical experience, and a passion for pushing the boundaries of what’s possible with AI.
Area of Expertise
Topics
AI Coding Agents and how to code them
AI Agents are the next big thing everyone has been talking about. They are expected to revolutionize various industries by automating routine tasks, mission critical business workflows, enhancing productivity, and enabling humans to focus on creative and strategic work. Of course, you can apply them to your everyday coding tasks as well.
In this talk we’ll go over what those agents can bring to the table of coding world, and why they can deliver the promise of coding smarter that the current generation of coding assistants can’t. We will then dive right into a quick live coding session where I’ll show what such agents can do in real life and how you can start using them to enhance your everyday life already right after the talk. And we’ll finish off with some remarks on what the future of programming might look like in the near future as those agents get included into your everyday life.
Will AI (finally) replace developers?
Are software developers about to become obsolete? You've probably seen the headlines: "AI will take over coding jobs," "Robots writing software," or even "The end of programming as we know it." But is the hype real, or just another exaggeration?
In this talk, we'll unpack the truth behind today's powerful AI coding assistants. How close are these tools to fully replacing human developers? Can AI truly write creative, reliable, and secure code without supervision, or is it still just sophisticated autocomplete?
Join me as we explore the current state of AI in software development, uncovering its strengths, limitations, and surprising capabilities. Rather than fearing replacement, I'll present a bold vision for the future—one where developers and AI collaborate in entirely new ways, reshaping our roles and redefining what it means to be a programmer.
Developing production-ready apps in collaboration with AI Agents
AI Agents are the next big thing everyone is talking about. They are expected to revolutionize various industries by automating routine tasks, mission critical business workflows, enhancing productivity, and enabling humans to focus on creative and strategic work. Of course, you can apply them to your everyday coding tasks as well. But just like with any other AI or non-AI-based tool, you need to understand how to use it correctly in order to maximize your benefits.
In this workshop, you'll get to experience AI coding agents first-hand as we collaborate with them in real time to build a production-ready app from scratch. For that, we will use Zencoder, an AI coding agent platform that empowers developers to ship products faster. We will be building the app in Python, and ideally, you already have some programming experience in Python to get the most out of the session. You will also need to bring your laptop with either VSCode or JetBrains (PyCharm) installed.
Going beyond copilot with AI Agents
In this talk, we'll talk about past, present and future of coding assistants. I will go over the problems of the current generation of assistants and what is causing them. Then we'll dive into way to solve those issues, namely, AI Agents. I'll talk about them in general, why and how they can help actually deliver the promise of "coding faster and smarter" and what is needed to realize those agents. We will then dive deeper into how they can be applied specifically to coding to make your everyday life easier. And we'll finish off with some examples of the ways you can incorporate such agents into your workflow already right after this talk.
LLMs, Meet Your Tools: The Magic of Model Context Protocol
Model Context Protocol (MCP) is a recent innovation that's quickly gaining traction across the developer ecosystem - and for good reason. It offers a powerful way to extend LLM capabilities by enabling seamless access to external tools, APIs, and data sources directly from within the context of your IDE.
In this talk, we’ll unpack what MCP is, the problems it solves, and why it’s a key enabler for building more intelligent, context-aware workflows. We’ll walk through how to integrate existing MCP servers and how to easily build your own to unlock custom capabilities. You’ll also see real-world examples of chaining multiple MCPs together and connecting them to external systems like Grafana, databases, and internal APIs to supercharge productivity - no window switching required.
Whether you’re a Developer, DevOps, or ML Engineer, MCP opens the door to faster iteration, smarter automation, and context-rich coding experiences. If you care about productivity and developer experience in the age of LLMs, you should care about MCP.
Supercharging DevOps with MCP (Without Opening a Security Hole)
Model Context Protocol (MCP) is a powerful new way to extend LLMs with real-time access to tools, APIs, and infrastructure. It enables seamless workflows like querying Grafana dashboards, triggering CI/CD jobs, or fixing issues from Sentry all without leaving your IDE. In this talk, we’ll explore how MCP works, how to build your own MCP servers, and how to compose them to automate Ops tasks and boost productivity across your stack.
But as we wire LLMs into our systems, security becomes a critical concern. Unrestricted use of MCP can open the door to various vectors of attack. We’ll cover main areas of concern as companies start adopt MCP tools - and discuss how to use them safely in production environments.
NDC Copenhagen Developers Festival 2025 Sessionize Event Upcoming
Web Summer Camp 2025 Sessionize Event Upcoming
NDC Oslo 2025 Sessionize Event Upcoming
Lead Innovation Day 2025 Sessionize Event Upcoming
Blipz on the Radar 2025 Sessionize Event
Porto Tech Hub Conference 2024 Sessionize Event
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