talk-data.com

​Shipping real AI products is now one of the most in-demand engineering skills, but most teams still get stuck turning prototypes into something that actually works.

​In this podcast, AI engineer and bestselling author Paul Iusztin breaks down the full AI engineering skill stack:

• ​The principles behind production-grade systems
• ​How to build reliable agentic workflows
• ​The LLMOps practices that keep models stable
• ​The patterns he’s learned from shipping more than 20 AI applications

​We’ll also go beyond the code. Paul will share how he structures his work, teaching, writing, and professional growth, and how he uses AI tools to stay focused, productive, and consistent.

​Join us live if you want a straightforward look at the technical and personal side of modern AI engineering. ​ ​About the Speaker: ​Paul Iusztin is an AI engineer committed to helping developers create fully functional, production-grade AI products. He is the author of the bestselling "LLM Engineer’s Handbook," leads the Agentic AI Engineering course, and is a founding AI engineer at a startup based in San Francisco. He also Decoding AI Magazine, where he assists engineers in moving beyond the proof-of-concept stage to build more effective AI systems.

​With over ten years of experience, Paul teaches comprehensive AI engineering, covering everything from data gathering to deployment, monitoring, and evaluation. He emphasizes robust software practices, infrastructure, and principles that are reliable in a world increasingly influenced by AI coding tools.

Join our Slack: https://datatalks.club/slack.html

​LLMs are powerful, but they still hallucinate facts, especially when asked about entities, relationships, or claims that require up-to-date or structured knowledge.

​In this hands-on workshop, we'll explore how to use Wikidata as a grounding and fact-checking layer for LLMs to reduce hallucinations and make AI systems more reliable.

​We'll start with a short introduction to Wikidata and then set up the Wikidata MCP so an LLM can retrieve and verify facts rather than relying solely on its internal memory. This already provides a practical way to ground LLM outputs in verifiable data.

​From there, we’ll go beyond LLM-only approaches and build a small experimental fact-checking pipeline. The system combines semantic retrieval, LLM-based reranking, and natural language inference (NLI) to validate claims against evidence in a more controlled and interpretable way.

​This workshop focuses on evidence-driven verification pipelines that make LLM's reasoning steps explicit and easier to inspect, debug, and improve.

​What we'll cover:

• ​Wikidata as a structured source for factual verification
• ​Setting up and querying Wikidata using MCP
• ​Verifying claims with MCP + an LLM
• ​Moving beyond pure GenAI to evidence-based fact-checking
• ​Finding relevant Wikidata statements with semantic search
• ​Ranking candidate evidence with an LLM
• ​Verifying claims using an NLI model

​​What you'll leave with By the end of the workshop, you'll be able to:

• Ground LLM outputs in structured data to reduce hallucinations
• ​Understand when LLM-only fact-checking is not enough
• ​Build a small, transparent fact-checking pipeline you can adapt to real projects

​About the speaker:

​Philippe Saadé is the AI/ML project manager at Wikimedia Deutschland. His current work focuses on making Wikidata accessible to AI application with projects like the Wikidata vector database and the Wikidata Model Context Protocol.

Join our Slack: https://datatalks.club/slack.html ​

​This event is sponsored by Wikimedia

​Alexey Grigorev, the course creator, will officially start the new cohort of the Data Engineering Zoomcamp in this live session. He’ll walk you through the course structure, key topics, and what you’ll build.

​What You’ll Learn During the Session

​Alexey will walk you through:

• ​What’s included in the course: topics, tools, and hands-on projects
• ​How assignments, feedback, and scoring work
• ​How to approach the material, even if you’re new to ML
• ​What it’s like to learn together with thousands of learners in the DataTalks.Club community

​You’ll also have a chance to ask Alexey your questions live.

​Thinking About AI Dev Tools Zoomcamp?

​Data Engineering Zoomcamp is a free 9-week course covering infrastructure setup, workflow orchestration, data warehousing, analytics, batch processing, and streaming. The last three weeks focus on a capstone project in which you'll build an end-to-end data pipeline using a dataset of your choice, demonstrating data lake and warehouse solutions with documentation. Projects are peer-reviewed by fellow participants. ​The new cohort of the Data Engineering Zoomcamp starts on January 12, 2026. You can join by registering here. ​

​About the Speaker

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series. ​Alexey is a seasoned software and ML engineer with over 10 years of engineering experience and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books, including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge. ​

Join our slack: https://datatalks.club/slack.html

Build a Multi-Agent Deep Research System with Temporal - Alexey Grigorev

​In this hands-on workshop, you'll build a durable deep-research agent and learn how to make LLM-powered systems reliable enough for real production environments.

​We’ll walk through:

• ​Building a deep-research agent step by step
• ​Handling failures and unpredictable LLM behavior
• ​Designing agentic workflows with Temporal + PydanticAI

​By the end of the workshop, you'll know how to take an idea from PoC to a production-grade multi-agent system with Temporal: observable, fault-tolerant, easy to extend, and designed to survive real-life conditions. ​ ​About the speaker:

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series.

​Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge. ​

​​​​​​​DataTalks.Club is the place to talk about data. Join our slack community! ​

​This event is sponsored by Temporal.

How modern ML workflows evolve from human-supervised pipelines to scalable, agent-driven feedback loops — with concrete examples and real-world transitions.

​Outline:

1. ​Human-in-the-Loop (HITL): Foundations and Limitations

2. ​What HITL means in practice (guided feedback loops, evaluation, corrections).

3. ​Key limitations: scalability, latency, reasoning gaps, context sensitivity.

4. ​Where HITL still shines: accuracy, safety, human effectiveness.

5. ​Agent-in-the-Loop (AITL): The Next Evolution Step

6. ​What changes when agents become active participants in the loop.

7. ​Architectural view: planning, tool-use, continuous improvement, automation.

8. ​Strengths: adaptivity, speed, scalable labeling, generalization.

9. ​Real-World Comparison & When Each Paradigm Wins

10. ​HITL vs AITL across accuracy, trust, cost, transparency, and scalability.

11. ​HITL-critical domains: medical, autonomous driving, manufacturing.

12. ​AITL-favored areas: fraud detection, recommender systems, logistics.

13. ​Transition & Future Outlook

14. ​Human-in-the-loop → human-on-the-loop → human-over-the-loop.

15. ​Hybrid approaches combining human judgment with agent autonomy.

​ About the Speaker:

Ertuğrul Mutlu is a Computer Engineering student at RWTH Aachen University and a Werkstudent Researcher at Fraunhofer IAIS (Enterprise Information Systems). His work spans reliable AI systems, agentic workflows, applied LLM engineering, and signal‑processing‑based feature extraction.

He focuses on building practical, lightweight AI systems that bridge classical methods with modern LLM‑driven agent architectures. He recently published a preprint on wavelet‑based feature engineering and clustering, writes technical articles on dev.to about ML systems and agentic AI, and actively contributes to the open‑source and data/ML community through prototypes, research notes, and talks.

**Join our slack: https://datatalks.club/slack.html**

Curious about the Data Engineering Zoomcamp? Join us for a live, interactive Q&A session with course creator Alexey Grigorev and get all your questions answered before the new cohort begins on January 12, 2026.

​What You’ll Learn During the Session

​Alexey will walk you through:

• ​Course curriculum: An overview of the topics, tools, and real-world projects you'll work on
• ​Assignments and grading: How homework and peer reviews are structured
• ​Getting help and feedback: How support works during the course and in the community
• ​Portfolio-building projects: Which hands-on projects will you build during the course to showcase your skills
• ​Learning with the community: How to engage with 79k+ learners in the DataTalks.Club Slack

​Alexey will also share tips on how to follow the material effectively, pace your learning, and stay motivated throughout the course. ​You’ll get a chance to meet the instructor, learn more about the course structure, and ask your questions. ​

​Thinking About Data Engineering Zoomcamp?

​Data Engineering Zoomcamp is a free 9-week course covering infrastructure setup, workflow orchestration, data warehousing, analytics, batch processing, and streaming. The last three weeks focus on a capstone project in which you'll build an end-to-end data pipeline using a dataset of your choice, demonstrating data lake and warehouse solutions with documentation. Projects are peer-reviewed by fellow participants. ​The new cohort of the Data Engineering Zoomcamp starts on January 12, 2026. You can join by registering here. ​

​About the Speaker

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series. ​Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge.

Join our slack: https://datatalks.club/slack.html

Improving LLM prompts using data-driven feedback optimization - Mikhail Sveshnikov

​Outline:

• ​Overview of prompt optimization challenges and common approaches (manual iteration, few-shot learning, etc.)
• ​How Evidently AI's prompt optimization works: using feedback from mistakes on real data to iteratively improve prompts
• ​Live demonstration: optimizing a classification prompt step-by-step, showing how errors are identified and used to refine the prompt
• ​Q&A and discussion: best practices, when to use different strategies, and practical consideration

​ ​​About the Speaker:

​Mikhail Sveshnikov is an AI engineer at Evidently AI with 10+ years in ML and MLOps, focused on building developer tools for reliable and measurable AI in production. ​

Join our Slack: https://datatalks.club/slack.html

​During this session, we’ll take a practical look at the Analytics Engineer role: what it actually covers, how it fits into modern data teams, and which skills matter most.

​Rather than a step-by-step tutorial, this talk focuses on core concepts, real examples, and recurring patterns that define the work of Analytics Engineers today.

​We’ll cover:

• ​What the Analytics Engineer role really includes and how it complements data engineers, data scientists, and business teams
• ​Technical foundations that keep an AE effective: SQL, data modeling, testing, version control, and development workflows
• ​Soft skills that quietly shape impact: cross-team communication, stakeholder alignment, and systematic thinking

​The talk draws on key insights from Fundamentals of Analytics Engineering, with Juan sharing lessons learned while writing the book and working with data teams. ​By the end, you’ll have a grounded view of why the Analytics Engineer role exists, how it has evolved, and which capabilities are worth prioritizing if you want to advance in this career. ​

​About the speaker: ​Juan Manuel Perafan is an analytics engineer, educator, and community builder based in Utrecht. He’s the co-author of Fundamentals of Analytics Engineering, host of the SQL Lingua Franca podcast, and a dbt Community Award winner. Juan founded the Analytics Engineering Meetup Netherlands and the Dutch dbt Meetup, and has spoken at events like dbt Coalesce, Linux Foundation OS Summit, and Big Data Expo NL.

**Join our slack: https://datatalks.club/slack.html**

Alexey Grigorev is hosting a live hands-on workshop to explore how Docker can simplify your data workflows, from setting up databases to packaging your scripts for reproducibility. ​This session is open to everyone interested in learning practical Docker skills for data engineering and analytics. ​During the workshop, we’ll walk through a complete workflow using Docker, PostgreSQL, pgAdmin, and Docker Compose, showing how to run and connect multiple services with minimal setup effort. ​ ​What you’ll learn:

• ​Why Docker is essential for modern data work
• ​Running PostgreSQL in a Docker container and connecting it to your local environment
• ​Connecting with pgcli or directly from Jupyter notebooks
• ​Loading and exploring the NYC Taxi dataset
• ​Managing databases visually with pgAdmin 4 (latest UI)
• ​Converting notebooks to scripts and Dockerizing them
• ​Running multi-container setups with Docker Compose
• ​Understanding Docker networking, port mapping, and volumes

​The workshop will be recorded and later used to refresh the Docker module of the Data Engineering Zoomcamp, so you’ll also get a preview of what’s coming in the new course release. ​ ​Thinking about DE Zoomcamp? ​Data Engineering Zoomcamp is a free 9-week course on building production-ready data pipelines. The next cohort starts in January 2026. Join the course here. ​ ​About the Speaker ​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series. ​​Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge.

Join our slack: https://datatalks.club/slack.html ​

​In this podcast episode, we’ll be joined by Sofya Yulpatova, Founder and CEO of a PetTech startup building what many describe as an early version of the “Apple Watch for dogs.” Her work sits at the intersection of machine learning, sensor data, and real-world behaviour patterns, and she brings a refreshingly honest view of what it takes to make pet health measurable.

​We'll discuss the challenges in animal health technology compared to human wearables, such as dogs' unpredictable behavior and the difficulty of collecting useful data. Sofya will explain why many early health signals are often undetectable by owners but clear in the data. ​We’ll also cover the technical side, including developing models for different dog breeds, managing sensor noise, and creating feedback loops with veterinarians and pet owners.

​Topics we plan to explore:

• ​Why sleep patterns may be the strongest and most overlooked health indicator
• ​How small daily behaviour changes can reveal early discomfort
• ​The realities of collecting embedded sensor data in the real world
• ​Challenges around calorie estimation, device variability, and multi-dog generalization
• ​Lessons from early prototypes and testing with real pets

​This episode explores how machine learning, sensor data, and behavioral science intersect, demonstrating how applied machine learning can advance pet health technology to meet expectations similar to those of human wearables. ​

​About the Speaker:

​Sofya Yulpatova is the Founder and CEO of Fit Tails, a PetTech startup developing an activity and health tracker for pets. She has a background in computer science, machine learning, and product management, and previously managed product and delivery operations at FixParts, an international automotive parts distributor. Sofya studied at the University of Latvia and completed the Sales and Marketing Programme at the Stockholm School of Economics in Riga.

Join our slack: https://datatalks.club/slack.html

​Alexey Grigorev, the course creator, will officially start the new cohort of the AI Dev Tools Zoomcamp in this live session. He’ll walk you through the course structure, key topics, and what you’ll build. ​ ​What You’ll Learn During the Session

​Alexey will walk you through:

• ​What’s included in the course: topics, tools, and hands-on projects
• ​How assignments, feedback, and scoring work
• ​How to approach the material, even if you’re new to ML
• ​What it’s like to learn together with thousands of learners in the DataTalks.Club community

​You’ll also have a chance to ask Alexey your questions live. ​ ​Thinking About AI Dev Tools Zoomcamp? ​AI Dev Tools Zoomcamp 2025 is a free 6-week course that takes you from experimenting with AI coding assistants to building your own coding agent and automating workflows. Over six modules, you’ll learn vibe coding, build and deploy a React + FastAPI project, extend assistants with the Model Context Protocol (MCP), create an AI agent that scaffolds Django apps, apply AI in testing and DevOps, and use low-code tools like n8n for automation.

​The new cohort of the AI Dev Tools Zoomcamp starts on November 18, 2025. You can join by registering here. ​ ​About the Speaker

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series. ​Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge.

Join our slack: https://datatalks.club/slack.html

Physics-based AI models such as neural networks, neural operators, and operator transformers - Aditya Seshaditya

We will leverage quantum machine learning techniques to enhance fluid dynamics simulations using physics-informed AI models and their quantum counterparts (Quantum PINNs). The workshop will explore various implementations, including attention-enhanced architectures. The goal is to demonstrate the potential of quantum computing in solving high-dimensional partial differential equations (PDEs) associated with fluid dynamics, improving both computational efficiency and accuracy.

Open-source frameworks: PennyLane (QML), NVIDIA PhysicsNemo (PINNs)

In this workshop, we will cover the following steps:

• Physics-inspired models
• Training and Loss-Physics
• Hybrid quantum-classical approaches

By the end of this workshop, you’ll understand the details of AI models used for simulations such as CFD (Computational Fluid Dynamics) and the relevance of physics-based approaches.

About the speaker:

Aditya Seshaditya is a Data Scientist with background in Quantum Computing, Digital Twins and AI.

Join our slack: https://datatalks.club/slack.html

​How resilience and inclusion shape better teams – Xia He-Bleinagel

​We will explore what it means to rebuild a career in technology and grow into leadership after a major life change. The session will look at how resilience, curiosity, and continuous learning can open new paths in data and cloud, especially when re-entering the workforce after time away. Drawing from practical experiences, it will touch on the mindset shifts, support systems, and habits that make career reinvention possible in a fast-moving field.

​The conversation will also highlight the human side of leadership that inclusive practices, empathy, and mentorship can help teams perform better and stay connected. It will examine how organizations can better support women and parents in tech, why visibility and representation matter, and what it takes to build confidence and belonging in technical environments.

​She will cover:

• ​Reflections from Xia’s first 100 days as Head of Data and Cloud
• ​Building a high-performing, empathetic data team
• ​Returning to tech after a career break and finding confidence
• ​Empowering women and mothers through inclusion and mentorship

​About the Speaker:

​Xia He-Bleinagel is Head of Data and Cloud at N O W GmbH, a German federal organization advancing zero-emission mobility and sustainable technology. After taking time off to raise her children, she returned to the workforce and built a successful career in data and cloud engineering.

​Through continuous learning and community involvement, she rose to a leadership role where she now focuses on building inclusive teams, empowering women in tech, and leading with empathy.

Join our slack: https://datatalks.club/slack.html

Curious about the AI Dev Tools Zoomcamp 2025? Join us for a live, interactive Q&A session with course creator Alexey Grigorev and get all your questions answered before the new cohort begins on November 18, 2025. ​ ​What You’ll Learn During the Session

​Alexey will walk you through:

• ​Course curriculum: An overview of the topics, tools, and real-world projects you'll work on
• ​Assignments and grading: How homework and peer reviews are structured
• ​Getting help and feedback: How support works during the course and in the community
• ​Portfolio-building projects: Which hands-on projects you will build during the course to showcase your skills
• ​Learning with the community: How to engage with 79k+ learners in the DataTalks.Club Slack

​He’ll also share tips on how to follow the material effectively, pace your learning, and stay motivated throughout the course.

​You’ll get a chance to meet the instructor, learn more about the course structure, and ask your questions. ​ ​Thinking About AI Dev Tools Zoomcamp?

​AI Dev Tools Zoomcamp 2025 is a free 6-week course that takes you from experimenting with AI coding assistants to building your own coding agent and automating workflows. Over six modules, you’ll learn vibe coding, build and deploy a React + FastAPI project, extend assistants with the Model Context Protocol (MCP), create an AI agent that scaffolds Django apps, apply AI in testing and DevOps, and use low-code tools like n8n for automation.

​The new cohort of the AI Dev Tools Zoomcamp starts on November 18, 2025. You can join by registering here. ​ ​About the Speaker

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series. ​Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge. ​

Join our slack: https://datatalks.club/slack.html

​MCP (Model Context Protocol) is rapidly becoming the new standard for connecting AI models with practical tools.

This hands-on workshop will examine how MCP links AI models like Claude to real-world tools, allowing developers to automate, expand, and monitor their workflows.

​We’ll cover:

• What is MCP: Definitions, Architecture, Capabilities
• Connecting and configuring the MCP tools inside Claude
• Using the MCP Inspector to explore and debug tool capabilities
• Building practical developer workflows with Git MCP, Claude Code, and Code Review MCP

By the end of this workshop, you’ll be able to incorporate MCP tools into your development environment, add custom capabilities to AI models, and build more efficient, context-aware workflows. ​ ​About the speaker:

Bhavani Ravi runs Flowexperts.ai, a consulting agency that helps companies adopt and build AI agents backed by data systems. She has a decade of experience building Backend systems and data platforms.

Bhavani is also an Apache Airflow Champion, international tech speaker, and LinkedIn Learning instructor. She loves teaching and explores that via corporate training under TheLearningDev. She has taught companies Python Backend, Langgraph, and MCP

Join our slack: https://datatalks.club/slack.html

​Ivan Potapov - Research Engineer, Zalando SE

In this workshop, we fine-tune Qwen models with parameter-efficient adapters using two complementary approaches: Soft Prompt token tuning and LoRA SFT, with an optional KL-anchored SFT term to keep the model’s behavior close to the base while adding new styles and formats. You’ll see how to prepare open-source data (Dolly 15k), render with chat templates, run short training loops, and monitor validation loss/perplexity with stepwise evaluations.

A tiny KL toy example explains per‑token contributions to H(P)\, H(P\,Q)\, and KL(P\|\|Q)\, making the “anchoring” intuition concrete. By the end\, you’ll know how to apply Soft Prompt for quick style steering\, LoRA for deeper adaptation\, and KL regularization to reduce drift and forgetting—plus how to save/load LoRA adapters for deployment.

Notebook.

​About the speaker:

Ivan Potapov is a Research Engineer at Zalando, specializing in search. He has taught workshops on data engineering, AI agents, and LLM alignment, helping practitioners bridge software engineering with applied machine learning.

Join our slack: https://datatalks.club/slack.html

​Image Classification with PyTorch: ML Zoomcamp Module Update - Alexey Grigorev

​This is the fourth workshop in our ML series on ML model deployment and engineering.

​In the ML Zoomcamp course, our Deep Learning module has traditionally focused on TensorFlow and Keras. But PyTorch has rapidly become the dominant framework for deep learning.

​In this workshop, we’ll demonstrate how to implement key concepts, like convolutional neural networks, transfer learning, and training loops, using PyTorch.

​Led by Alexey Grigorev, this hands-on workshop demonstrates how to rewrite a TensorFlow/Keras project into PyTorch and train image classifiers.

​What you’ll learn:

• ​How to set up a deep learning project in PyTorch
• ​How to implement convolutional neural networks (CNNs) from scratch
• ​How to apply transfer learning with pre-trained models like MobileNet
• ​Key differences between TensorFlow/Keras and PyTorch
• ​How to handle data preprocessing and augmentation in PyTorch
• ​How to evaluate, checkpoint, and improve your models

​By the end, you’ll have a working PyTorch training pipeline and an understanding of how it maps to the TensorFlow/Keras version.

​Like the other workshops, this will be a live demo with practical tips and time for Q&A. ​

​Thinking About ML Zoomcamp?

​This workshop reflects the updated Deep Learning module (Module 8) in the ML Zoomcamp. You’ll get a preview of how the course now includes both TensorFlow and PyTorch, so you can choose the framework that fits your workflow.

​ML Zoomcamp is our free 4-month course that takes you from beginner to advanced ML engineer. It covers the fundamentals of ML, from regression and classification to deployment and deep learning.

​The new cohort of the ML Zoomcamp starts on September 15, 2025. You can join it by registering here. ​

​About the Speaker

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series.

​Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge.

Join our slack: https://datatalks.club/slack.html