Embedded Systems

Hey! 😊 Ich gebe eine **kostenfreie** Embodied Breathwork Journey - eine ruhige, regulierende Session mit Atem, Körperwahrnehmung und sanfter Bewegung. Es geht nicht um intensives „Durchbruch“-Breathwork, sondern darum, in deinem eigenen Tempo wieder mehr bei dir anzukommen - im Körper, beim Atem, im Nervensystem. **✨ Was dich erwartet:** \- geführte Atemübungen \- einfache somatische Übungen \- sanfte Bewegung & Ausdruck \- Integration & Entspannung Du kannst jederzeit selbst bestimmen, wie tief du gehst. **💭 Besonders passend, wenn du…** \- viel im Kopf bist und wieder mehr fühlen willst \- Stress oder innere Unruhe hast \- Breathwork entspannt kennenlernen möchtest 🕒 Dauer und Kosten: Ca. 90 Min. und **kostenfrei** 📍 Berlin, Prenzlauer Berg (OR Natural Balance Studio, Immanuelkirchstr. 22 in 10405 Berlin) am Sonntag 26.4. um 13 Uhr 👥 Kleine Gruppe **Bitte sei 10 Minuten vor Beginn des Events da, damit wir pünktlich anfangen können.** Am Ende gehst du eher ruhiger, klarer und mehr bei dir raus - nicht aufgewühlt.

Join us in Berlin for an evening dedicated to the present and future of mobile development with Mendix. In the first session, a developer from BlueBerk will share real-world insights from a recently completed large-scale Mendix Native project. The talk will cover the current state of native development, common limitations teams face today, and practical workarounds that proved successful in production. In the second session, a Product Manager from Mendix will provide a forward-looking perspective on mobile development with the Mendix platform. He will discuss the available mobile options today and what’s coming next, helping you understand how to choose the right approach for your project. The presentation will compare native mobile and Progressive Web App (PWA) strategies and introduce the PWA Wrapper as a flexible and practical alternative for many scenarios. Whether you are currently building mobile apps or planning your next Mendix project, this meetup will give you valuable hands-on experience, architectural guidance, and a clear view of the platform’s mobile

**🏆 Win a free ticket to [DASH26](https://dash.datadoghq.com/)!** We’re hosting an on-site raffle where the grand prize is a ticket to Datadog’s annual conference in New York City. \-\-\-\- All talks will be **presented in English**, to ensure that as many people as possible can participate and engage at this event. **If you want to attend, please RSVP to secure your spot - this will make organizing easier. Thank you so much ♥️** **Location:** [The-B Berlin, Revaler Str. 32, 10245 Berlin](https://www.theb-berlin.com/) \-\-\-\-\-\- **🏠 18:00 - Arrival: Networking, Drinks & Snacks (30 min.)** Grab yourself snacks & drinks and say hello to everybody else! **📅 18:30 - Introduction & What's new at Datadog? (15 min.)** **🎙️**Speaker: Marcel Drechsler, User Group Leader & Product Owner Internal Developer Platform @ **[andsafe](https://andsafe.de)** Introduction into the evening and highlights of Datadog's recent new features and products. **📅 18:45 - Powering Platform Engineering through Datadog (30 min.)** **🎙️**Speaker: Marcel Drechsler, User Group Leader & Product Owner Internal Developer Platform @ **[andsafe](https://andsafe.de)** In the rapidly changing landscape of Platform Engineering, Datadog has evolved from a monitoring tool into a comprehensive foundation for Internal Developer Platforms (IDPs). This session explores the journey of scaling observability and security into a unified platform strategy that reduces developer friction. We will dive into how Datadog’s expanding ecosystem provides the essential building blocks for modern self-service infrastructure. Attendees will learn how to leverage these integrated features to build a more resilient and transparent developer experience. Discover how to transform your Datadog instance into a strategic asset for your platform’s success. **📅 19:15 - Logs as a First-Class Citizen - How Lightspeed Commerce evolved logs to unlock the full power of Datadog** **(30 min.)** **🎙️**Speaker: Rein Martha, Staff Software Engineer, Lightspeed Commerce When Lightspeed started with Datadog, we didn't begin with traces or metrics — we began with evolving our logs. Raw, unstructured, and full of noise. The first step was making them worth keeping: trimming duplicates, removing what no one ever read, and transforming what remained into structured, queryable signals. That foundation changed everything. Once logs became first-class — with clean attributes, consistent structure, and a clear purpose for every line — the rest of the observability stack followed naturally. Monitors built on log queries. Dashboards that actually meant something on incidents. Metrics generated directly from log attributes, giving us long-term retention without the cost of keeping everything raw. **📅 19:45 - Best Practices for Alerting with Datadog (30 min.)** **🎙️**Speaker: Santiago Gomez Saez, Datadog ambassador & Principal Cloud Architect @ **[dxone](https://www.dx.one.gmbh/)** Operational excellence is the main objective of SRE teams. Focusing on alerting, this talk shares common pitfalls and best practices on how and when to alert when incidents occur. In addition, we show how to self-heal in some cases requiring no manual intervention. **🥗 20:15 - Drinks, Food & Networking** Enjoy refreshments while networking with community peers! **👋 21:00 - Goodbye, see you next time!**

\*\*\*DEUTSCHE VERSION UNTEN STEHEND\*\*\* 🌟 Calling all Soulful and Energetic Voices that wanna tell stories! 🌟 Hey there, vibrant souls! 🎤 Are you ready to ignite the stage with your youthful energy and passion for music? Join our electrifying urban pop & musical ensemble, where voices come together in a celebration of song and joy! 🎶 Picture this: a dynamic fusion of historic and contemporary pop, musical hits, and soulful melodies, all brought to life by voices bursting with youthful exuberance! 🎵If you're between 15 and 45 and crave the thrill of harmonizing with fellow music lovers, this is your golden ticket! 🌈 Rehearse with us every Thursday from 7:30-10 pm in the heart of Kreuzberg, and experience the sheer exhilaration of making music with kindred spirits! 💃🕺 So, what are you waiting for? We're on the lookout for singers who bring their prior solo and ensemble experience to the mix – voices that stand out and harmonize seamlessly with the sound of the ensemble. 🌟 Are you ready to add your voice to our chorus of excitement? Send us a private message expressing your interest, vocal range, and any singing experience you bring to the table. Let's turn up the volume on fun and create memorable musical moments together! 🎉 🎶 **Day doesn't fit, too little singing experience, or not in the required age group? No problem!** I conduct several choirs with different profiles: **Shabach! *– the choir not only for shy people*** (https://www.meetup.com/de-DE/shabach-berlin-the-choir-not-only-for-shy-people/) **DEUTSCHE VERISON:** Liebe Nachbarn, wir haben 2023 das neue urbane Pop- & Musical-Ensemble "SHOWTIME!" in Kreuzberg 61 ins Leben gerufen, Altersspanne ca. 15-45 Jahre, in englischer und deutscher Sprache. Wir singen Popsongs, Musicals, und Filmmusik. Das Level ist für Fortgeschrittene und die Sänger\*innen sollten über eine gewisse Gesangserfahrung verfügen. Der Chor probt **jeden Donnerstag von 19:30-22:00 Uhr im Gewölbekeller der Kapelle-am-Urban, Grimmstr. 10, Berlin-Kreuzberg.** Falls es Dich interessiert mitzumachen: Schreib mir bitte vorab Dein Interesse und Deine Stimmgruppe / Erfahrung kurz per Privatnachricht. Danke. **Keine Zeit an dem Tag, zu wenig Gesangserfahrung oder außerhalb der Altersgruppe? Kein Problem!** Ich leite Chöre mit verschiedenen Profilen: **Shabach! *– der Chor nicht nur für Schüchterne*** (https://www.meetup.com/de-DE/shabach-berlin-the-choir-not-only-for-shy-people/)

Join our in-person meetup on April 24th to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. **[Register to reserve your seat.](https://voxel51.com/events/berlin-ai-ml-and-computer-vision-meetup-april-24-2026)** Space is limited! **Date, Time and Location** Apr 24, 2026 5:30 PM - 8:30 PM [MotionLab](https://motionlab.berlin/) Bouchéstraße 12/Halle 20 12435 Berlin **Kaputt: A Large-Scale Dataset for Visual Defect Detection** We present a novel large-scale dataset for defect detection in a logistics setting. Recent work on industrial anomaly detection has primarily focused on manufacturing scenarios with highly controlled poses and a limited number of object categories. Existing benchmarks like MVTec-AD (Bergmann et al., 2021) and VisA (Zou et al., 2022) have reached saturation, with state-of-the-art methods achieving up to 99.9% AUROC scores. In contrast to manufacturing, anomaly detection in retail logistics faces new challenges, particularly in the diversity and variability of object pose and appearance. Leading anomaly detection methods fall short when applied to this new setting. To bridge this gap, we introduce a new benchmark that overcomes the current limitations of existing datasets. With over 230,000 images (and more than 29,000 defective instances), it is 40 times larger than MVTec and contains more than 48,000 distinct objects. To validate the difficulty of the problem, we conduct an extensive evaluation of multiple state-of-the-art anomaly detection methods, demonstrating that they do not surpass 56.96% AUROC on our dataset. Further qualitative analysis confirms that existing methods struggle to leverage normal samples under heavy pose and appearance variation. With our large-scale dataset, we set a new benchmark and encourage future research towards solving this challenging problem in retail logistics anomaly detection. The dataset is available for download under [https://www.kaputt-dataset.com](https://www.kaputt-dataset.com). *About the Speaker* [Sebastian Höfer](https://www.linkedin.com/in/sebastian-h%C3%B6fer-891178121/) is an Applied Science Manager at Amazon Fulfillment Technologies & Robotics, leading machine learning and computer vision research for large-scale robotics and warehouse automation. He received his PhD from the Robotics & Biology Lab at TU Berlin, focusing on Sim2Real transfer and robotic perception. His recent work, “Kaputt: A Large-Scale Dataset for Visual Defect Detection” (ICCV 2025) [37], established a major benchmark for industrial anomaly detection, reflecting his expertise at the intersection of academic research and real-world deployment. **Data Foundations for Vision-Language-Action Models** Model architectures get the papers, but data decides whether robots actually work. This talk introduces VLAs from a data-centric perspective: what makes robot datasets fundamentally different from image classification or video understanding, how the field is organizing its data (Open X-Embodiment, LeRobot, RLDS), and what evaluation benchmarks actually measure. We'll examine the unique challenges such as temporal structure, proprioceptive signals, and heterogeneity in embodiment, and discuss why addressing them matters more than the next architectural innovation. *About the Speaker* [Harpreet Sahota](https://www.linkedin.com/in/harpreetsahota204/) is a hacker-in-residence and machine learning engineer with a passion for deep learning and generative AI. He’s got a deep interest in VLMs, Visual Agents, Document AI, and Physical AI. **Most AI Agents Are Broken. Let’s Fix That** AI agents are having a moment, but most of them are little more than fragile prototypes that break under pressure. Together, we’ll explore why so many agentic systems fail in practice, and how to fix that with real engineering principles. In this talk, you’ll learn how to build agents that are modular, observable, and ready for production. If you’re tired of shiny agent demos that don't deliver, this talk is your blueprint for building agents that actually work. *About the Speaker* [Bilge Yücel](https://www.linkedin.com/in/bilge-yucel/) is a Senior Developer Relations Engineer at deepset, helping developers build agentic AI apps with Haystack. Passionate about AI, she makes complex concepts approachable through hands-on tutorials, both online and at real-life events. **Operationalizing Computer Vision for Overhead Lines: Beyond the Demo** At first glance, visual inspection of high-voltage power lines seems straightforward: collect imagery, run one or two AI models, and report the findings. In practice, moving beyond a proof of concept reveals a range of issues that can make or break a campaign. Common concerns include data quality and coverage, scarcity of the most relevant cases and abundance everywhere else, variations in pylon geometry and asset types across regions, calibration and GIS alignment challenges, and a long tail of edge cases that emerge in real-world operations. This talk introduces Siemens Energy’s end-to-end overhead line inspection solution and shares key learnings from inspecting more than 10,000 km of power lines for real customers across several continents. We will show how raw 2D/3D data is transformed into structured information, delivering insights into asset inventory as well as defects, and supporting maintenance and planning decisions for critical infrastructure. The focus is on the combination of algorithmic building blocks and scalable processing, designed for robustness and consistency at scale, where even low error rates can become operationally significant. *About the Speaker* [Stefan Wakolbinger](https://www.linkedin.com/in/stefan-wakolbinger-aa0ba874/) is the Development Team Lead for AI & Analytics at SIEAERO, Siemens Energy's digital powerline inspection service. He leads the development of cutting-edge AI and analytics solutions that transform aerial powerline inspection through multi-sensor technology. His team creates digital twins of powerline infrastructure, automates fault detection, and monitors vegetation management—making powerline inspection safer, more precise, and more efficient. Stefan has been driving innovation in this role since September 2022. **Search your video library like a database** Drop in YouTube URLs or upload files and query content four ways: exact keyword matching, semantic search across transcripts, visual scene search via SigLIP2, and LLM-generated answers that synthesise across segments. [Paras Mehta](https://www.linkedin.com/in/pmehtaeu/) is a Berlin-based AI engineer and CTO/co-founder of Sylby, a language learning app he built from scratch, reaching 10,000 users and raising €350K. Previously: data scientist at Motionlogic, senior software engineer at Volkswagen, a PhD from Freie Universität Berlin, and a visiting stint at Cambridge. He now works as an AI engineer at HPI's AI Service Centre.

**Bitte mitbringen: 💶 3 Euro Gebühr (in bar oder Paypal), um die Meetup-Gebühren zu decken und als kleinen Ausgleich für die Orga. Danke! 🙏** . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . **Come together. Read. Talk about it.** Vielleicht liest du viel und vermisst Gespräche darüber. Vielleicht hast du Lust, neue Menschen kennenzulernen – in einem entspannten, ungezwungenen Rahmen. Lesen verbindet, und genau dafür ist dieser Club gedacht. Dieser *Social Reading Club* ist für Menschen, die gern lesen und sich genau das wünschen: mehr Zeit dafür – und Raum für Austausch mit anderen, die das genauso fühlen. Wir treffen uns in einem Café am **Platz der Luftbrücke in Kreuzberg**. Nicht als klassischer Buchclub mit Vorgaben oder Pflichtlektüre, sondern als gemeinsames Innehalten: jede\*r liest für sich, egal ob Zeitung, dicker Roman oder Sachbuch. Im eigenen Tempo. Danach kommen wir ins Gespräch – ganz natürlich, ohne Erwartung. Dein Handy kannst du dabei weglegen – ich behalte die Zeit für dich im Blick. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . **So sieht ein Treffen aus** Der Vormittag besteht aus **einer Leseeinheit**. Wir kommen an, bestellen etwas und richten uns ein. Dann lesen wir, zusammen, in Stille – konzentriert, jede\*r für sich. Zum Abschluss gibt es ein lockeres Kennenlernen und Austauschen – über das, was wir gerade lesen, und das, was es bei uns auslöst: Gedanken, Eindrücke, Stellen, die hängen geblieben sind. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . **ℹ️ Hinweise** * Wir treffen uns in einem Café und sind dort normale Gäste. Also plane bitte ein, dort etwas zu bestellen. * Eine Vorbereitung ist nicht erforderlich. Alles, was du tun musst, ist, etwas zum Lesen mitzubringen. * Das Treffen findet auf Deutsch statt. 🇩🇪 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . **🗓️ Agenda** **11:00 Uhr** Ankommen, Einrichten & etwas bestellen **11:15 – 12:30 Uhr** Stille Leseeinheit (konzentriertes Lesen, jede\*r für sich – gerne Kopfhörer mitbringen, falls es im Café etwas voller wird) **12:30 – 13:30 Uhr** Austausch, Kennenlernen & Ausklang

Dear data-loving community, we’re excited to invite you to our next Meetup! This time in collaboration with [Spiced Academy](https://www.spiced-academy.com/en), who will be hosting us at their space. Join us on April 23 in Berlin and bring all your questions! :) **Tom Kaltofen: *"Building Deterministic Context Layers for AI Agents"*** [Tom Kaltofen](https://www.linkedin.com/in/tomkaltofen/) is an Engineer at [DHL Data & AI](https://www.linkedin.com/company/dhl-data-ai/) and a Creator at [mloda.ai.](http://mloda.ai.) About his keynote: "Data access and reuse are still unsolved, and AI agents are making it worse. This talk goes deeper into that problem: AI agents depend on reliable context (data, features, intermediate state) to make correct decisions. In practice, this context is tied to specific pipelines or infrastructure, leading to brittle systems when moving from prototype to production. I'll show how a plugin-based approach lets teams build deterministic context layers: separating what you compute from how you compute it, so the same feature definitions work on a laptop and in production. The talk includes a live demo where an AI agent discovers and queries data features programmatically. " **Behnaz Derakhshani: *"What If I Started Today? Rethinking Career Switching in the AI Era"*** [Behnaz Derakhshani](https://www.linkedin.com/in/behnaz-derakhshani-63342775/) works as a Data Engineer at [Diconium](https://diconium.com). She shares her personal career shift from finance to data engineering, including the unfiltered challenges and lessons along the way. About her keynote: "Eight years ago, there was no AI to debug my logic, just documentation and Stack Overflow. Now as a Data Engineer, I’m breaking down the lessons learned from my finance to tech transition and why AI makes this the most exciting (and accessible) time to pivot." ✧ ✧ ✧ **What to expect:** * Two expert talks and Q&A * A welcoming atmosphere with networking opportunities * Some snacks & drinks to fuel your thoughts :) ✧ ✧ ✧ **Timetable:** * 18:30 - Event admission * 18:50 - Welcome & Introduction * 19:00 - Tom Kaltofen: *"Building Deterministic Context Layers for AI Agents"* * 19:30 - 5 minutes break * 19:35 - Behnaz Derakhshani: *"What If I Started Today? Rethinking Career Switching in the AI Era"* * 20:05 - Snacks, Drinks & Networking * 21:30 - End ✧ ✧ ✧ More on the **-> [applydata data engineering meetup page](https://applydata.io/data-engineering-meetup/)**. **Our goal is to form a local data-loving community, so join us and let's talk data together!** ✧ ✧ ✧ *At the event, sound, image and video recordings are created and published for documentation purposes as well as for the presentation of the event in publicly accessible media, on websites and blogs and for presentation on social media. By participating the event, the participant implicitly consents to the aforementioned photo and/or video recordings. Find [more information on data protection here](https://applydata.io/events/information-on-data-protection/).*