talk-data.com

Agenda:

• 18:30 - Opening doors of the venue

• 19:00 - Welcome to PyBerlin! // Organisers

• 19:10 - Welcome from the host - ThoughtWorks

• 19:20 - Conquering PDFs: document understanding beyond plain text // Ines Montani NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work with. In this talk, Ines will present a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem. Ines will show you how you can go from PDFs to structured data and even build fully custom information extraction pipelines for your specific use case.

Speaker's bio: Ines Montani is a developer specializing in tools for AI and NLP technology. She’s the co-founder and CEO of Explosion and a core developer of spaCy, a popular open-source library for Natural Language Processing in Python, and Prodigy, a modern annotation tool for creating training data for machine learning models.

• 19:50 - Short break

• 20:20 - Building EU-AI Act Compliant AI Agents for Legacy Systems // Aemal Sayer In this talk, Aemal will introduce a fully self-hosted, EU-AI Act compliant framework for building AI agents capable of operating any software system, legacy or modern, through its UI. Inspired by OpenAI’s Operator but designed for real-world compliance and flexibility, this framework combines LLMs, virtualization, and OS-level automation to let agents interact with applications as a human would: by clicking, typing, and navigating interfaces. Unlike API-bound or browser-focused tools, this solution enables true system-wide autonomy for AI agents, making integration with non-API systems not only possible, but seamless. The framework also embraces a human-in-the-loop design. When an agent encounters an issue it can’t resolve, it notifies a human operator, who can then remotely connect to the agent’s virtual environment, intervene to unblock the task, and hand control back to the agent to continue its work seamlessly.

Speaker's bio: Aemal Sayer is a freelance AI engineer based in Berlin, Germany, with over 20 years of experience in software development and 8 years specializing in artificial intelligence. He works with small and medium-sized businesses to automate financial processes such as bookkeeping, invoicing, and compliance. His focus is on building privacy-first, self-hosted AI agents tailored to industries like e-commerce, logistics, and manufacturing. Currently, he’s building a GDPR- and EU AI Act-compliant agent that integrates with DATEV, Germany’s leading accounting platform, as a public, open-source project, aiming to drive transparency and innovation in AI-powered business automation.

• 20:50 - Implementing Distributed Systems in Python // Shahriyar Rzayev In this talk, Shahriyar will demonstrate how to implement distributed systems patterns in Python through a step-by-step guide to building a distributed key-value storage system, filling a gap left by the abundance of examples in Go, Rust, and Java.

Speaker's bio: Software Engineer. Moving forward on Clean Code and Clean Architecture. Previous accomplishments include contributing to open source, providing technical direction, and sharing knowledge about Clean Code and Clean Architecture. An empathetic team player and mentor. Azerbaijan Python User Group Leader. Former QA Engineer and Bug Hunter.

• 21:20 - Closing session // Organisers

This event will be only in-person. Please check our Code of Conduct and official health regulation in Berlin before coming. If you feel some signs of sickness, please consider skipping this event and attending another time. We will have plenty of events in different formats in the future. Looking forward seeing you all soon!

This event is a collaboration with our friends from PyBerlin, check out their Meetup page here and sign up there!

-----

On the Agenda: • 18:30 - Opening doors of the venue • 19:00 - Welcome to PyBerlin! // Organisers • 19:10 - Welcome from the host - Thoughtworks

• 19:20 - Conquering PDFs: document understanding beyond plain text // Ines Montani NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work with. In this talk, Ines will present a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem. Ines will show you how you can go from PDFs to structured data and even build fully custom information extraction pipelines for your specific use case.

Speaker's bio: Ines Montani is a developer specializing in tools for AI and NLP technology. She’s the co-founder and CEO of Explosion and a core developer of spaCy, a popular open-source library for Natural Language Processing in Python, and Prodigy, a modern annotation tool for creating training data for machine learning models.

• 19:50 - Short break

• 20:20 - Building EU-AI Act Compliant AI Agents for Legacy Systems // Aemal Sayer In this talk, Aemal will introduce a fully self-hosted, EU-AI Act compliant framework for building AI agents capable of operating any software system, legacy or modern, through its UI. Inspired by OpenAI’s Operator but designed for real-world compliance and flexibility, this framework combines LLMs, virtualization, and OS-level automation to let agents interact with applications as a human would: by clicking, typing, and navigating interfaces. Unlike API-bound or browser-focused tools, this solution enables true system-wide autonomy for AI agents, making integration with non-API systems not only possible, but seamless. The framework also embraces a human-in-the-loop design. When an agent encounters an issue it can’t resolve, it notifies a human operator, who can then remotely connect to the agent’s virtual environment, intervene to unblock the task, and hand control back to the agent to continue its work seamlessly.

Speaker's bio: Aemal Sayer is a freelance AI engineer based in Berlin, Germany, with over 20 years of experience in software development and 8 years specializing in artificial intelligence. He works with small and medium-sized businesses to automate financial processes such as bookkeeping, invoicing, and compliance. His focus is on building privacy-first, self-hosted AI agents tailored to industries like e-commerce, logistics, and manufacturing. Currently, he’s building a GDPR- and EU AI Act-compliant agent that integrates with DATEV, Germany’s leading accounting platform, as a public, open-source project, aiming to drive transparency and innovation in AI-powered business automation.

• 20:50 - Implementing Distributed Systems in Python // Shahriyar Rzayev In this talk, Shahriyar will demonstrate how to implement distributed systems patterns in Python through a step-by-step guide to building a distributed key-value storage system, filling a gap left by the abundance of examples in Go, Rust, and Java.

Speaker's bio: Software Engineer. Moving forward on Clean Code and Clean Architecture. Previous accomplishments include contributing to open source, providing technical direction, and sharing knowledge about Clean Code and Clean Architecture. An empathetic team player and mentor. Azerbaijan Python User Group Leader. Former QA Engineer and Bug Hunter.

• 21:20 - Closing session // Organisers

RSVPS: Please sing up on the event page from PyBerlin!!! ------

Code of Conduct We adhere to the Berlin Code of Conduct to ensure a welcoming and respectful environment for all participants. The event space operates under largely compatible Thoughtworks Meetups & Events CoC.

Accessibility The Location is accessible for wheelchair users. This includes the entrance (no steps to get into the location), toilets and the stage.

On 2025-04-17, we will have 3 amazing speakers to share with you how AI can help you solve problems you may have. And thank you very much to Google Berlin for hosting us this time. Reserve your seats now and see you very soon!

Agenda

5:30 PM: Doors open, Registration, Dinner and Drinks

6:30 PM: Build with Gemini – Learn about Gemini's multimodal and agentic capabilities" + Q&A by Patrick Löber

Gemini 2.0 and 2.5 are the latest foundational models released by Google DeepMind, offering multimodal understanding, realtime interactions, text-to-image generations, thinking, and tool support for agentic use cases. In this talk you'll get an overview of Gemini's capabilities, learn about prototyping with Google AI Studio, and how to build with Gemini models.

7:00 PM: "Applied NLP in the Age of Generative" + Q&A by Ines Montani

Large Language Models (LLMs) and in-context learning have introduced a new paradigm for developing natural language understanding systems: prompts are all you need! Prototyping has never been easier, but not all prototypes give a smooth path to production. In this talk, titled "Reality is Not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI," I'll share the most important lessons we've learned from solving real-world information extraction problems in industry and show you a new approach and mindset for designing robust and modular NLP pipelines in the age of Generative AI.

7:50 PM: Break

8:00 PM: AI Engineering for Everyone + Q&A by Tejas Kumar

This talk dives deep into the landscape of AI in 2025 with a focus on agents and extending the capabilities of language models through Model Context Protocol (MCP). After this talk, the audience will have a holistic understanding of AI for 2025 and will be able to build real-world solutions with them.

8:50 PM: Drinks and Networking

Speakers

Patrick Löber - Google DeepMind (Developer Relationships Engineer)

Ines Montani - Explosion (CEO & Founder)

Ines is a software developer working on Artificial Intelligence and Natural Language Processing technologies, and the co-founder and CEO of Explosion (https://explosion.ai/) https://bsky.app/profile/inesmon…

Tejas Kumar - DataStax (Developer Relations Engineer)

Tejas Kumar is an international keynote speaker, best selling author, and host of the developer-loved ConTejas Code podcast with an engineering background spanning 23 years, from design to frontend to backend to devops. Today, Tejas shares talks at large with developer communities worldwide, equipping them to do their best work.

Hosted By

Alex Mir, GDG Organizer

GDG Berlin co-lead and Software Engineer

Emy Jamalian, QA engineer

I am a girl, a middle eastern, a European residence, an extra extroverted, a believer in making things work, a fighter for fairness, a motivator.

Jerome Mouton, Organizer

Louis Tsai, GDG Organizer

manjula dube, Organizer

I am Software Engineer & teacher. I'm a world renowned tech speaker.I am from India currently living in Berlin with my husband Sahil Mhapsekar.

I work at The Vanguard Group Europe. I am Founder of Geekabyte that aims to deliver in person tech workshops on Web Development & organises international conferences, React India & JS Conf India. I'm also a Google Developer Expert. I have been obsessed with coding ever since I graduated out of college.

I am founding member of Mumbai Women Coders that aims to encourage more women in tech & provide an avenue into the technology world. I love contributing to open source in my free time. I love Javascript, React & my family ❤️ In coming years I see my self teaching people to code.

Shrinish Donde,

Passionate about telecom and sports. Likes to be in organising and networking.

Mohamed Islem Ayari, Junior cloud Developper

Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-berlin-presents-using-ai-to-help-solve-problems-both-big-and-small/.

Agenda: • 18:30 - Opening doors of the venue

• 19:00 - Welcome to PyBerlin! // Organisers

• 19:10 - Welcome from the host - HeyJobs Gmbh

• 19:20 - Applied NLP with LLMs: Beyond black-box monoliths // Ines Montani Large Language Models (LLMs) have enormous potential, but also challenge existing workflows in industry that require modularity, transparency and data privacy. In this talk, I'll show some practical solutions for using the latest state-of-the-art models in real-world applications and distilling their knowledge into smaller and faster components that you can run and maintain in-house.

Speaker's bio: Ines Montani is a developer specializing in tools for AI and NLP technology. She’s the co-founder and CEO of Explosion and a core developer of spaCy, a popular open-source library for Natural Language Processing in Python, and Prodigy, a modern annotation tool for creating training data for machine learning models.

• 19:50 - Short break

• 20:20 - MLOps at HeyJobs: Building a Continuous Training Pipeline for Our Custom Embeddings Model // Viktor Bubanja and Shantanu Ladhwe As user behaviour and the relationship between users and jobs evolve over time, it’s crucial that our embeddings models powering Recommendations and Search capture these changes. In this talk, we’ll explore how we use AWS SageMaker to train and dynamically update embedding models to reflect the latest user-job relationships. We’ll dive into the MLOps challenges of handling model versioning, backfilling job embeddings, and managing rollbacks, sharing insights from our approach to keeping our Matching services up-to-date.

Viktor Bubanja speaker's bio: Viktor is a Senior Software Engineer in the Matching team at HeyJobs, where he is helping build the search and recommendations systems connecting talent with ideal job opportunities. His focus is on deploying ML systems into production and ensuring their scalability and reliability.

Shantanu Ladhwe speaker's bio: Shantanu is ML Engineering Manager at HeyJobs, where he works with a talented team of ML and Software Engineers to develop machine learning-driven search and recommendation systems for the job platform and has over 8 years of experience in Data Science, Machine Learning, MLOps, and NLP - now LMMs ;)

• 20:50 - Building Blinkist's Personalized Real-Time Recommendation Feed: From Design to Implementation // Idil Ismiguzel In this talk, I'll take you behind the scenes of how we revamped Blinkist's homepage with a real-time, personalized feed. I'll share how our system leverages multiple recommender algorithms and a ranking model (aka brain) to serve tailored content that boosts user engagement and retention. We’ll dive into how we utilize AWS Sagemaker to train these models and host models as endpoints, making real-time recommendations accessible for multiple services. From design to deployment, we will cover full journey of delivering impactful user experiences through smart personalization.

Speaker's bio: Idil is a Data Scientist and Machine Learning Engineer at Blinkist+Go1, where she helps drive personalized content and learning experiences. With a background in mobile gaming and tourism, she brings a diverse range of industry experience to her work. In addition to her work in ed-tech, Idil is a contributor to Towards Data Science on Medium, where she writes about machine learning, AI, and data science trends.

• 21:20 - Closing session // Organisers

This event will be only in-person. Please check our Code of Conduct and official health regulation in Berlin before coming. If you feel some signs of sickness, please consider skipping this event and attending another time. We will have plenty of events in different formats in the future. Looking forward seeing you all soon!

PyData Amsterdam 2024 is a 3-day event for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

Over the span of 3 days, attendees will have the opportunity to participate in workshops, attend live keynote sessions and talks, as well as get to know fellow members of the PyData Community.

Note: This is a paid event, to attend the event, Get your tickets here >

AGENDA Full Program >

Brief agenda below:

Wednesday, September 18 8:30 - 17:00 \| Tutorial day \| 8 x tutorials Full Program HERE

Thursday, September 19 8:00 - 9:00 \| Resgistration 9:00 - 10:20 \| Keynote \| Open-Source Multimodal AI by Merve Noyan Hugging Face 🤗 10: 35 - 17: 00 \| Talks by 21 speakers \| Check out the full program HERE 17:00 - 17:50 \| Lightening talks 17:50 - 18:00 \| Closing notes 18:00 - 20:00 \| Social events with Snowflake ❄️

Friday, September 20 8:00 - 9:00 \| Resgistration 9:00 - 10:20 \| Keynote \| Applied NLP in the age of Generative AI by Ines Montani Explosion 10: 35 - 16: 20 \| Talks by 23 speakers \| Check out the full program HERE 16:30 - 17:20 \| 17:20 - 17:30 \| Closing notes 18:00 - 18:30 \| Standup comedy

DIRECTIONS Location: Gedempt Hamerkanaal 231 1021 KP Amsterdam

PyData Amsterdam 2024 is a 3-day event for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

Over the span of 3 days, attendees will have the opportunity to participate in workshops, attend live keynote sessions and talks, as well as get to know fellow members of the PyData Community.

Note: This is a paid event, to attend the event, Get your tickets here >

AGENDA Full Program >

Brief agenda below:

Wednesday, September 18 8:30 - 17:00 \| Tutorial day \| 8 x tutorials Full Program HERE

Thursday, September 19 8:00 - 9:00 \| Resgistration 9:00 - 10:20 \| Keynote \| Open-Source Multimodal AI by Merve Noyan Hugging Face 🤗 10: 35 - 17: 00 \| Talks by 21 speakers \| Check out the full program HERE 17:00 - 17:50 \| Lightening talks 17:50 - 18:00 \| Closing notes 18:00 - 20:00 \| Social events with Snowflake ❄️

Friday, September 20 8:00 - 9:00 \| Resgistration 9:00 - 10:20 \| Keynote \| Applied NLP in the age of Generative AI by Ines Montani Explosion 10: 35 - 16: 20 \| Talks by 23 speakers \| Check out the full program HERE 16:30 - 17:20 \| 17:20 - 17:30 \| Closing notes 18:00 - 18:30 \| Standup comedy

DIRECTIONS Location: Gedempt Hamerkanaal 231 1021 KP Amsterdam

** Important RSVP here. (Due to room capacity, it's required to pre-register at the link for admission).

Along with our friends at Explosion and Rasa, we are hosting a pre-party for PyCon DE where the teams behind Metaflow, SpaCy, and Rasa will discuss their journey so far, what’s new, and where these projects are headed in 2024! ​ Ines Montani (spaCy, Explosion) will talk about "Incorporating LLMs into practical NLP workflows", giving us a behind the scenes look at her PyCon DE talk "The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs";

​Tanja Bunk (Rasa) will speak about "CALM Down, It's Just a Paradigm Shift: Moving from Intent-Based NLU to LLM-Powered Dialogues"; ​ Hugo Bowne-Anderson (Metaflow, Outerbounds) will talk about "Building GenAI and ML systems with OSS Metaflow." ​ More detailed agenda to come!

* The event is hosted by AICamp partner: Outerbounds.

Agenda:

• 18:00 - Opening doors of the venue

• 18:20 - Welcome to PyBerlin! // Organisers

• 18:30 - Welcome from the host // Native Instruments

• 18:40 - 19:10 - The CPU in your browser: WebAssembly demystified // Dr. Antonio Cuni

In the recent years we saw an explosion of usage of Python in the browser: Pyodide, CPython on WASM, PyScript, etc. All of this is possible thanks to the powerful functionalities of the underlying platform, WebAssembly. In this talk we will examine what is exactly WebAssembly, what are the strong and weak points, what are the limitations and what the future will bring us. We will also see why and how WebAssembly is useful and used outside the browser. This talk is targeted to an intermediate/advanced audience: no prior knowledge of WebAssembly is required, but it is required to have a basic understanding of what is a compiler, an interpreter and the concept of bytecode. The introduction will cover the basics to make sure that the talk is understandable also by people who are completely new to the WebAssembly world, but after that we will dive into the low-level technical details, with a special focus on those who are relevant to the Python world, such WASI vs emscripten, dynamic linking, JIT compilation, interoperability with other languages, etc.

Speaker's bio: Dr. Antonio Cuni is a Principal Software Engineer at Anaconda. He is a core developer of PyScript and PyPy, and one of the founders of the HPy project, which aims to design a better and more modern C API for Python. He loves to write tools from developers for developers, such as Pdb++, fancycompleter and vmprof and he is creator/maintainer/contributor of numerous other open source projects. He have also been very active in the Python community for years, giving talks at various conferences such as EuroPython, EuroSciPy, PyCon Italia, and many others. He regularly writes on the PyPy blog and on the HPy blog. His main areas of interest are compilers, language implementation, TDD and performance.

• 19:10 - 19:30 - Four Key Enabling Questions for Agile Delivery //Paul Hammond

This talk will share an approach to agility for use by your team members, your team and your organisation, using four simple Key Enabling Questions.

Speaker's bio: Paul is the CTO at Native Instruments, and has previously held senior leadership positions at Microsoft, Skype, eBay and Zoopla.

• 19:30 - 19:50 - Short break • 19:50 - 20:20 - Incorporating LLMs into practical NLP workflows // Ines Montani

In this talk, I'll show how large language models such as GPT-4 complement rather than replace existing machine learning workflows. Initial annotations are gathered from the OpenAI API via zero- or few-shot learning, and then corrected by a human decision maker using an annotation tool. The resulting annotations can then be used to train and evaluate models as normal. This process results in higher accuracy than can be achieved from the LLM alone, with the added benefit that you'll own and control the model for runtime.

Speaker's bio: Ines Montani is a developer specializing in tools for AI and NLP technology. She’s the co-founder and CEO of Explosion and a core developer of spaCy, a popular open-source library for Natural Language Processing in Python, and Prodigy, a modern annotation tool for creating training data for machine learning models.

• 20:20 - 20:50 - Live Web Hacking: Server Takeover via a Single Python Vulnerability // Shahriyar Rzayev

This technical session will focus on a live demonstration of exploiting a Server-Side Template Injection (SSTI) vulnerability in a Python web application. The demonstration will illustrate the process of using an SSTI vulnerability to gain initial access to a server, followed by a privilege escalation to obtain root access. Detecting SSTI: Methods for identifying SSTI vulnerabilities within Python web applications. Exploitation Technique: Step-by-step exploitation of the identified SSTI vulnerability to gain control over the server. Privilege Escalation: Techniques to escalate privileges from a lower-privileged shell to root access.

Speaker's bio: Senior Software Engineer at Nord Security. Azerbaijan Python User Community leader. Focused on Security, Architecture and Python

• 20:50 - Closing session // Organisers

This event will be only in-person. Please check our Code of Conduct and official health regulation in Berlin before coming. If you feel some signs of sickness, please consider skipping this event and attending another time. We will have plenty of events in different formats in the future.

Looking forward seeing you all soon!

If you like cool talks about 🧑‍🔬 Data Science, 🤖Artificial Intelligence, 🐍 coding or 🤗 community, the Big PyData BBQ is the place to be! 🔥

KÖNIGSWEG and hei_INNOVATION invite you to join the 5️⃣th edition of the annual big gathering of the PyData Südwest community. Besides talks there will be a lot of time for networking over a delicious 🥦+🍖 BBQ .

This year's topic: Large Language Models 🔥🤩

Confirmed Speakers

1. Ines Montani (ExplosionAI / spaCy)
2. Alejandro Saucedo (Director of Eng, Science, Product & Analytics Zalando / Institute for Ethical AI & Machine Learning)
3. Michael Gertz (Institute of Computer Science, Heidelberg University)
4. Alina Lenhardt (Cerence)

The event will be live streamed and published on PyDataTV.

18:00 Welcome 👋 📺 18:20 Talk Ines Montani 📺 19:00 BBQ 🍖🥦 UPDATE: 20:30 🛋️ Panel: Alejandro, Alexander, Alina, Ines, Michael 📺 UPDATE: 21:30 ⚡ Lightning Talks. 📺 UPDATE: 21:30 Networking. 🍻 UPDATE: 22:00 End. 📺 = live stream 🍖🥦, 🍻 = locally, only

About our speakers:

Ines Montani, a renowned software developer, is a co-founder of Explosion AI, a digital laboratory specializing in artificial intelligence and machine learning. She is a lead developer of spaCy, a widely used open-source library for advanced natural language processing (NLP) in Python. Together with Matthew Honnibal, she also developed Prodigy, a machine learning annotation tool that aids in the efficient creation of training data. Montani is an advocate for OSS, working tirelessly to make the fields of AI and ML more accessible.

Alejandro Saucedo is a technology entrepreneur and software engineer known for his work in machine learning and artificial intelligence. He is Director of Eng, Science, Product & Analytics at Zalando and the Chief Scientist at The Institute for Ethical AI & Machine Learning, a London-based research organization focused on developing best practices for machine learning and artificial intelligence, among others. Saucedo has a strong technical background and has worked in software development, ML and data science. He has spoken at numerous events and is promoting ethical practices in AI development

Michael Gertz is a full professor at Heidelberg University where he heads the Database Systems Research Group at the faculty of Mathematics and Computer Science. He received his diploma in Computer Science from the TU Dortmund University, and his Dr. rer. nat. from the Leibniz University of Hannover in 1996. From 1997 until 2008 he was a faculty at Department of Computer Science at the University of California at Davis. His interdisciplinary research interests include text analytics, data mining, complex networks, and scientific data management, with applications in the medical sciences, law, physics, political sciences, and economics.

Alina Lenhardt is a computational linguistat at Cerence and Program Committee Chair at PyConDE & PyData Berlin 2023.

Alexander Hendorf is one of the organizers of PyData Südwest and is heavily involved in the Python & PyData community. For him, contributing to open source and the community means giving something back, as his company Königsweg uses open source to implement Data Science & AI for its customers.

⚡️ Lightning Talks (5 min. each)

1. Alessandro Angioi - Supercharge your language learning journey with Python 2. Bela Stoyan - Automatically transform complex python methods to polars expressions 3. Irina Smirnova-Pinchukova - Croshapes - using graph to design a toy

😍 A big thank you to our sponsors:

• hei_INNOVATION, for hosting the meetup.
• KÖNIGSWEG, for supporting the organization.
• NUMFOCUS, for promoting open source software.
• Python Softwareverband e.V., for support.

Contact If you have any questions or suggestions, please feel free to contact us via:

• Meetup
• Want to speak? Submit a talk here.
• Interested in hosting an event? Here's our Info-Deck & contact to the organisers!