April 10, 2026

From Training to Production: Lightweight ML Validation and Monitoring

Catch silent ML failures before they reach production! This session demonstrates lightweight, practical techniques to validate and monitor ML models across their lifecycle. Using tools like DeepChecks and Evidently AI, attendees will learn how to detect data drift, evaluate model quality, and ensure trust in their models with minimal effort.

Gift Ojeabulu

I’ve spent the last 6+ years at the intersection of AI/ML, SWE, developer advocacy, and community building. Most recently, I worked as an AI devrel advocate and content lead at Iterative.ai, the team behind the popular open source AI tools DVC and CML. I’ve built and scaled thriving AI communities, notably as co-founder of D.C.A, now the largest Data and AI community of Black professionals worldwide. A visionary data scientist whose work is transforming Africa's technological landscape. As the Co-founder of Data Community Africa, an advisory board member at DevNetwork (Artificial Intelligence), and AI Developer Advocate, Gift has emerged as a pivotal figure in democratizing data and AI across the continent. My crowning achievement, the African Data Community Newsletter, has become a beacon of knowledge sharing, reaching an impressive network of over 2500 subscribers spanning 45 countries and 8 U.S. states. This initiative has inspired his involvement at DatafestAfrica with 4 Conferences and 5+ hackathons in less than 4 years, now one of the continent's premier data and AI conferences, bringing together practitioners, researchers, and enthusiasts from across the globe. In Lagos, Gift's leadership of the MLOps community has revolutionized how organizations approach machine learning operations. Under his guidance, the community has become a hub for innovation in practical MLOps and Large Language Models (LLMs), fostering collaboration between industry leaders and emerging talents. His emphasis on open-source AI development has created new pathways for African developers to contribute to global technological advancement. Through strategic initiatives and unwavering dedication, Gift Ojeabulu continues to architect the future of Africa's data and AI ecosystem. His work exemplifies how individual leadership can catalyze continental transformation, making advanced technology accessible to communities that have historically been underserved in the global tech landscape.

Measuring Experiments in LLMs: A/B Tests and Automated Testing

Even small changes in LLMs can impact output quality, safety, and user experience. In this talk, we’ll show how to log experiments with Langfuse, automate tests with Pytest, and enrich them using Hypothesis-generated random data scenarios. Participants will learn how to use code, tests, and data-driven A/B tests to improve LLM development.

Kader Miyanyedi, Özge Çinko

I have been a backend developer for 4 years, working primarily with Python and Django. I enjoy sharing what I’ve learned at previous PyCon talks and through writing on Medium, helping others improve their coding and AI skills.,

Beyond the Prompt: Building Research Agents in Python

LLMs can answer questions, but can they conduct research? Real research requires planning, data gathering, synthesis, and refinement. This talk explores Python patterns for orchestrating multi-step workflow to create autonomous research agents. We'll deconstruct the agentic architecture, from DAG-based planning to reflection loops, and show how to implement these concepts using practical Python patterns.

Simona Skiotytė

As a Software Developer for the Generative AI platform at Nasdaq, Simona Skiotytė specializes in architecting the integration of Generative AI systems on AWS. Key projects include the integration of a research system that automates query generation, iterative web search, and multi-stage report synthesis, all orchestrated in AWS. Simona's experience extends to building secure and scalable cloud infrastructure. She architected a multi-tenant data platform with comprehensive test coverage and audit logging. Simona also developed a framework for an AWS cross-account data ingestion into vectorstore featuring complex IAM roles, presigned URLs for secure file management with KMS encryption, and lifecycle orchestration using AWS Step Functions. Additionally, she built a CRUD API for managing version-controlled, reusable Generative AI prompt templates. Simona's foundation in data science comes from her time at ETH Zürich, where she applied statistical and mathematical models to large-scale biological datasets, utilizing dimensionality reduction, clustering, and regression modeling. This background provides a strong analytical lens through which Simona approaches the construction of Generative AI systems.

When Space Weather Breaks Your GPS: Building an Explainable Early Warning System

Have you ever happened to use GPS and realised that it is not working properly? The Sun could be responsible. We'll see a **real-world forecasting system** designed to predict a Space Weather phenomenon affecting GNSS accuracy and radio communications. The system is based on **CatBoost** and integrates space- and ground-based data. The talk focuses on **model design and evaluation choices**, showing how interpretability and uncertainty-aware forecasting can be combined in a real-time operational pipeline.

Vincenzo Ventriglia

A results-driven data professional, focused on hype-free solutions tailored to business needs. I currently create value at the **National Institute of Geophysics and Volcanology**, where I develop machine learning models in the **Space Weather** domain. My work is complemented by finding the hidden stories in data and make them accessible to stakeholders. I studied Physics in Italy (Napoli) and Germany (Frankfurt am Main), previously worked in Analytics within the strategic division of the world's largest professional services network, as well as in the Data Science department of Italy’s leading publishing group. I am also an organiser of **PyData Roma Capitale**, actively involved in building the local Python and data science community. Outside of work, I enjoy theatre, discussing finance, and learning new languages.

30 min

XAI - Explainable AI tools and techniques

In this talk, I propose to discuss the problem of building explainable AI with the two approaches - causal vs correlational. I will talk about what mech interp in LLMs. As a way to understand how models answer questions by looking inside them and checking which neurons activate when. I will discuss Anthropic's open sourced a python module - circuit-tracer, the Neuronpedia portal , will also talk about my own work with "activation cube" data structure (this is not a standard - I came up with it)

Viraj Sharma

I am a passionate technologist with a strong interest in Python, artificial intelligence and Edge computing. I am currently studying in Class 9 at Presidium School, Delhi, INDIA. I have worked in areas such as torch.nn visualization, Anthropic technologies (MCP, Skills), large concept models, and TensorCore/CUDA benchmarks, Edge AI on raspbrry pi running small models with sensors. Recently I have been working on XAI (AI explaianability) and putting my work as a project on my AI Lab - modelrecon.com. As an active member of the Python community and AI communities, I enjoy learning from experienced developers and sharing my insights with others. I attend major tech events including PyCons, Linux Fests, OS Summits, GDG events, p99conf, and various AI conferences, where I actively present my projects and ideas.

Building Production-Ready On-Device Rewrite: Speed, Robustness, and Customer Impact

I'll discuss building capabilities on top of on-device language models, with Rewrite as a case study – a publicly available paraphrasing skill that is widely used across Microsoft's products. I'll cover comprehensive data collection strategies, carefully designed adapters training and evaluation. I'll discuss the engineering challenges we faced: achieving target latency while maintaining quality, hardening the system against edge cases, and how to deliver the technology to partners and the lessons learnt.

Marat Saidov

Marat Saidov is a Senior Software Engineer at Applied Sciences Group, Microsoft. Based in Belgrade, Serbia. Previously improved Speech Recognition and Natural Language Understanding services at Alice Voice Assistant, Yandex. Besides that, he was an NLP Research Assistant at HSE University, Russia.

Context Engineering with DeepAgents: Write, Select, Compress, Isolate

Context Engineering is the new prompt engineering. As agentic workflows grow, just appending messages to a list causes context poisoning and latency spikes. In this talk, we'll look at a better architecture using the `deepagents` library. We'll explore the four pillars of context engineering: Write, Select, Compress, and Isolate. You'll learn how to treat context as a finite resource and build autonomous agents that can solve complex tasks without crashing your context window.

Antanas Daujotis

With over 20 years in the trenches of engineering, he now focuses on the messy reality of getting agentic systems to work in production.

Multi-Model LLM Orchestration in Python: A Case Study in Research Automation

How do you turn thousands of PDFs into actionable insights? This talk shows how we built a Python-based AI assistant using LLMs and RAG to automate literature reviews: covering architecture, trade-offs, and real lessons from production use in policy research.

Mauro Pelucchi

Mauro Pelucchi is Senior Data Scientist and Big Data Engineer responsible for the design of the “Real-Time Labour Market Information System on Skill Requirements” for CEDEFOP (European Centre for the Development of Vocational Training). He currently works as Head of Global Data Science at Lightcast with the goal to develop innovative models, methods, and deployments of labour market data and other data to meet customer requirements and prototype new potential solutions. His main tasks are related to advanced machine learning modelling, labour market analyses, and the design of big data pipelines to process large datasets of online job vacancies. In collaboration with the University of Milano-Bicocca, he took part in many research projects related to the labour market intelligence systems. He collaborates with the University of Milano-Bicocca as a Lecturer for the Masters of Business Intelligence and Big Data Analytics and with the University of Bergamo as a Lecturer in Computer Engineering.

Spec-Driven Development with Kiro: From Software Developer to AI Agent Orchestrator

In this session, we explore Specification-Driven Development (SDD) and its implementation in the Kiro IDE. You will see how machine-readable specifications drive the entire lifecycle—from EARS-based requirements to automatically generated code, tests, and documentation. The session also highlights the industry shift from developers as coders to developers as orchestrators of AI agents, defining intent and architecture while AI executes and validates the implementation.

Haim Michael

Haim Michael is a software development trainer, entrepreneur, and lecturer with nearly 30 years of experience. He founded life michael (lifemichael.com), delivering professional training in Java, Python, JavaScript, Scala, Kotlin, and more. Haim has lectured at leading universities, including Bar-Ilan, HIT, Shenkar, and Technion, and has trained developers at top tech companies. He also organizes international developer conferences—XtremeJ, XtremeJS, and XtremePython—bringing global communities together. Earlier in his career, he developed over 200 mobile games and applications at Jacado for mobile phones, working with 200+ companies worldwide. He holds an MBA (summa cum laude) and multiple industry certifications, and he is passionate about teaching and shaping the future of software development.

What It Means to Be a CTO in an AI Startup Today

**I haven't written a single line of code in over a year.** As CTO of an AI startup, I've fully embraced vibe coding: orchestrating AI to generate production-ready code. 🔍 **Highlights** 1. **The paradigm shift:** from autocompletion to full project generation 2. **My 3-step workflow:** voice prompts, deep research, code generation 3. **The judgment trap:** why expertise matters more than ever You'll leave with practical techniques to ship 10x faster!

Fabien Vauchelles

Fabien Vauchelles brings 20+ years of experience in product design and software development. He holds a dual degree from Université Paris-Sud in Engineering and Master Research in Distributed Systems. A serial entrepreneur, Fabien has founded three companies including Zelros, where he served as CTO for six years building the AI platform from scratch. He is now CTO and Co-founder of an AI startup, applying vibe coding principles daily. Recognized internationally as an expert in AI, distributed systems, and data science, Fabien has spoken at conferences in 15+ countries on topics including web scraping, anti-bot systems, and open-source tooling. He is also the creator of Scrapoxy, a popular open-source web scraping tool.