The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for AI_dev Europe 2025 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.
This schedule is automatically displayed in Central European Summer Time, CEST (UTC +2). To see the schedule in your preferred timezone, please select from the drop-down menu to the right.
IMPORTANT NOTE: Timing of sessions and room locations are subject to change.
Sign up or log in to add sessions to your schedule and sync them to your phone or calendar.
All attendees may feel free to use the Zen Zone as needed. It is a physical space where attendees can go if for any reason they can’t interact with other attendees at that time where conversation and interaction are not allowed.
Ricardo leads the Platform Infrastructure team at CERN with a strong focus on cloud native deployments and machine learning. He has led for several years the internal effort to transition services and workloads to use cloud native technologies, as well as dissemination and training... Read More →
General Manager, AI & Infrastructure, The Linux Foundation
Mark Collier is a longtime open-source strategist and the current General Manager, AI & Infrastructure at the Linux Foundation. He co-founded both the OpenStack project and the OpenInfra Foundation, guiding a small NASA–Rackspace collaboration into one of the most active open-source... Read More →
Thursday August 28, 2025 09:00 - 09:10 CEST Auditorium
Malte Pietsch is CTO & Co-Founder at deepset, where he builds Haystack and the deepset AI Platform to enable developers all over the world to build, optimize, and embed LLM applications efficiently in their products and processes. Before founding deepset in 2018, he conducted NLP... Read More →
Thursday August 28, 2025 09:10 - 09:25 CEST Auditorium
Associate Professor, Computer Science Department, Columbia University
I am an Associate Professor at the Computer Science Department, Columbia University. I am also a co-founder of Arklex.ai that centers its efforts on harnessing the power of AI Agents to empower and shape the future landscape of the workspace. Before that I was an Assistant Professor at UC Davis. I received my PhD at Language Technology Institute under School of Computer Science, Carnegie Mellon University... Read More →
Thursday August 28, 2025 10:00 - 10:15 CEST Auditorium
Vutukuri Sreenivas is a tech enthusiast buzzing with excitement about how innovation shapes our world. A final-year B.Tech student at Presidency University, Bangalore, he’s diving into DevOps and cloud-native tech, exploring tools like Kubernetes. Sreenivas mentors coders at Google... Read More →
When an ML engineer deploys a Stable Diffusion model to Kubernetes, they unwittingly create an attack surface unlike anything traditional security teams have encountered. I discovered this firsthand after our "perfectly secured" AI cluster was compromised.
I am Site Reliability Engineer at KodeKloud . I am an Open source contributor, evaluating and contributed in various open source tools and projects, such as, Microsoft's Open source libraries, OpenCV, SUSE, etc. I was also a Google Summer of Code contributor 2022 and a GitHub Extern... Read More →
Thursday August 28, 2025 11:15 - 11:40 CEST G001-002
Vibe coding is an amazing force multiplier. What about code's sidekick, data? Working with data could be like that too! We'll walk through a multi-agent system for data analysis, schema creation and knowledge graph construction.
We'll see how to: - generate a schema from a pile of files, then import them - generate a schema for a domain, then synthesize the data - attach hints for later retrieval
Andreas is a technological humanist. Starting at NASA, Andreas designed systems from scratch to support science missions. Then in Zambia, he built medical informatics systems to apply technology for social good. Now with Neo4j, he is democratizing graph databases to validate and extend... Read More →
Thursday August 28, 2025 11:15 - 11:40 CEST Auditorium
The allure of AI automating complex infrastructure management on AWS, Azure, and GCP is strong. Promises of self-healing systems, predictive scaling, and optimized resource utilization abound. However, the core principles of Site Reliability Engineering – prioritizing stability, reliability, and predictability – clash with the "black box" nature and potential unpredictability of AI. This session dives into the SRE perspective, exploring the inherent risks of letting current AI models directly manage production Kubernetes clusters and cloud resources. We'll outline the non-negotiable safeguards, controls, and observability required before SREs can cautiously embrace AI, moving from hype to hardened reality. Learn practical approaches like GitOps integration, policy enforcement, human-in-the-loop validation, and robust monitoring needed to bridge the gap between AI's potential and production safety.
Krishnendu Dasgupta is an engineer with 14+ years in applied Machine Learning . His interests span across healthcare, generative AI, and decentralized AI. He is currently applying AI innovation in clinical trials, graph ML, NLP, and privacy-preserving AI. A Stanford Code in Place... Read More →
LLMs have democratized AI, making it more accessible for everyone. But today’s chat bots still feel very disconnected. Wouldn’t it be great if you could use AI to tap into your personal knowledge and data, and use it to drive the tools you already know and love? Imagine using a chat bot to create your next pitch deck, or generating bespoke 3D scenes for your next home decoration project using inexpensive tools like Blender. In this talk, I'll show you how this is possible with tools like Genkit and MPC, the Model Context Protocol.
Peter is a Staff Developer Advocate on the Firebase at Google, helping developers build amazing experiences and high quality apps using Firebase and AI.
Thursday August 28, 2025 11:50 - 12:15 CEST Emerald Room
As the scale of AI models and training datasets grows, so does the complexity of efficiently feeding data into GPU-accelerated training workloads. Traditional I/O stacks are becoming a bottleneck—especially in cloud native environments—where elasticity and performance must go hand in hand. This talk introduces an open-source, Arrow-based data cache for distributed training workloads on Kubernetes and tabular datasets stored as Apache Iceberg tables.
Ricardo is making daily impactful contributions as an AI Infrastructure Lead at Snowflake. He's passionate about open source in various roles, such as co-chairing the CNCF TAG-Runtime and leading the Cloud Native AI Working Group. With over 25 years of experience in the tech industry... Read More →
Andrey Velichkevich is a Senior Software Engineer at Apple and is a key contributor to the Kubeflow open-source project. He is a member of Kubeflow Steering Committee and a co-chair of Kubeflow AutoML and Training WG. Additionally, Andrey is an active member of the CNCF WG AI. He... Read More →
Thursday August 28, 2025 11:50 - 12:15 CEST G001-002
In the rapidly evolving landscape of artificial intelligence, Vision-Language Models (VLMs) have emerged as powerful tools capable of understanding and interpreting both visual imagery and natural language. In this talk, we’ll dive into VLMs and how they work without getting bogged down in tech jargon.
Dr. Satya Mallick is the CEO of OpenCV.org - the non-profit that maintains the largest computer vision library in the world. He is the founder of Big Vision LLC, a computer vision and AI consulting company. Previously, Dr. Mallick co-founded Sight Commerce Inc., where he led the team... Read More →
We’d like to invite all attendees who identify as women or non-binary to join each other for a networking lunch at the event. We will begin with a brief introduction and then attendees will be free to enjoy lunch and mingle with one another. All attendees must identify as a woman or non-binary and must be registered for the conference to attend.
We will do our best to accommodate all interested attendees, but please note that participation is on a first-come, first-served basis.
Thursday August 28, 2025 12:15 - 13:35 CEST RAI Amsterdam
EVE (Earth Virtual Expert) is an open-source domain-specific large language model designed to democratize access to Earth Observation (EO) and Earth Science (ES) knowledge. Backed by the European Space Agency and developed by Pi School and Imperative Space, EVE bridges AI and EO through domain-adaptive pre-training, instruction tuning, and Retrieval-Augmented Generation. It supports multiple user groups—from scientists and students to journalists and decision-makers—by enabling factual, source-grounded, and explainable interactions with EO content. This talk outlines EVE’s training pipeline, data compliance approach, performance benchmarks, and open-source contributions, including models, datasets, and legal compliance guides. We'll also share lessons from human evaluations, infrastructure challenges, and our roadmap toward an EO digital assistant.
Àlex R. Atrio is a Senior Deep Learning Scientist at Pi School in Rome, leading development on EVE, an open-source LLM for Earth Observation and Earth Science in collaboration with ESA’s Φ-lab. He holds a PhD in Machine Translation from EPFL/HEIG-VD and has a background in NLP... Read More →
Antonio Lopez is a passionate developer with a Master's degree in Artificial Intelligence from the University of Bologna, specializing in Computer Vision and Natural Language Processing.
Vijayasri Iyer is a Machine Learning Scientist at Pi School, where she has led multiple international teams in developing Generative AI solutions. She holds a Bachelor’s degree in IT, Master’s in AI and certifications in Technology Policy and AI Safety.
Imagine deploying a complex AI model for real-time inference, but facing latency that slows down your application. We've all been there. This talk isn't just about theoretical serverless benefits; it's about real-world performance gains. We'll show you how we slashed inference latency from several seconds to under 100 milliseconds, achieving a 10x improvement in throughput, by harnessing the power of serverless on Kubernetes.
Paras has been an active speaker sharing his technical expertise at Google tech conferences, Linux Foundations Open source summit in Japan and North America. Paras is a highly skilled backend developer with a passion for information retrieval and a knack for translating complex technical... Read More →
Anmol is a seasoned International Tech Speaker (delivered 75+ talks), a Distinguished Guest Lecturer, an active conference organizer, and has published several notable papers. He works at Google and focuses on Emerging Technologies.
Thursday August 28, 2025 13:35 - 14:00 CEST G001-002
The frontier in AI models is shifting from general purpose LLMs (like GPT-4o) to advanced reasoning models. Models like OpenAI o1 and DeepSeek-R1 can now think through the question; and they excel in math and coding benchmarks.
This talk first describes how these models are taught to reason on hard questions. We then talk about DeepSeek-R1, a state of the art open source model. We conclude by examining DeepSeek's desirable properties and why it took the world by storm.
I'm the co-founder at Ubicloud, an open source alternative to AWS.Previously, I was a partner at Microsoft, leading PostgreSQL engineering teams. I came to Microsoft through its acquisition of Citus Data. I was the cofounder and CTO at Citus, and I learned a lot about doing startups... Read More →
Thursday August 28, 2025 13:35 - 14:00 CEST Auditorium
In October 2024 the Open Source Initiative (OSI) unveiled the Open Source AI Definition (OSAID) v.1, concluding a multi-year, world-wide community effort.
Stefano joined OSI in 2021 after decades of open source advocacy, both as a contributor and leader. He co-founded and led the Italian chapter of FSFE from 2001 to 2007, structured the developer community of the OpenStack Foundation and subsequently led open source marketing teams... Read More →
Enterprises struggle to integrate fragmented generative AI (GenAI) technologies. Due to its rapid evolution and diverse implementations, even top LLMs hallucinate when answering Kubernetes-related questions.
LF AI & Data TAC Board/Chairperson | Open Source AI Evangelist at Intel, Intel
Passionate about helping people discover the exciting world of artificial intelligence, Ezequiel is a frequent AI conference presenter and the creator of use cases, tutorials, and guides that help developers adopt open source AI tools.
Andreas is a technological humanist. Starting at NASA, Andreas designed systems from scratch to support science missions. Then in Zambia, he built medical informatics systems to apply technology for social good. Now with Neo4j, he is democratizing graph databases to validate and extend... Read More →
Thursday August 28, 2025 13:35 - 14:35 CEST Emerald Room
In this talk, we will introduce two open-source projects vLLM and KServe and explain how they can be integrated to leverage better performance and scalability for LLMs in production. The session will include a demo showcasing their integration.
Rafael Vasquez is a software developer on the Open Technology team at IBM. He previously completed an MASc. working on self-driving car research and transitioned from a data scientist role in the retail field to his current role where he continues to grow his passion for MLOps and... Read More →
Thursday August 28, 2025 14:10 - 14:35 CEST G001-002
Recent research has raised concerns about LLM-generated code exhibiting significant similarity to their training data, raising potential legal issues with incompatible software licenses. While Xu et al. established a benchmark for evaluating this phenomenon through their LiCoEVAL benchmark, showing small but significant portions of LLM outputs containing "notably similar" code to existing open-source implementations, these findings were limited by the scope of their reference dataset.
Oscar Enrique Goñi is a systems engineer who graduated from the National University of the Center of the Province of Buenos Aires, Faculty of Exact Sciences (Argentina, 2009), and holds a Ph.D. in Computer Science from the National University of La Plata (Argentina, 2015). Since... Read More →
Software development is seeing a shift in how humans and AI interact. What began as simple code completion and suggestion within the IDE has become so much more. We're now seeing AI agents function like pair programming partners, similar to junior developers who can take on GitHub issues but still need guidance and review. At Coder, we've been testing AI agents within our Cloud Development Environments by letting them tackle actual development tasks. In this talk, I'll show you where AI pairing partners excel (documentation, quick prototyping) and where they still struggle. I'll also explore what's coming next: the shift toward "peer programming" where AI becomes a more trusted partner with greater autonomy. You'll see real examples of productivity gains we've measured, learn how to provide isolated environments for safe AI interaction, and walk away with practical steps to start leveraging AI's evolution from helpful assistant to development partner. Whether you're just experimenting with code assistance or ready to deploy AI agents at scale, this session will help you navigate this rapidly changing technology.
Nicky Pike is a Developer Relations lead at Coder after spending 20+ years making developers' lives easier at some of tech's biggest names. From launching Xbox Live to rebuilding how CVS Health develops software, he's helped shape developer productivity and team experiences at Microsoft... Read More →
Thursday August 28, 2025 14:10 - 14:35 CEST Auditorium
Cities are responsible for over 70% of global greenhouse gas (GHG) emissions, yet only 5% have GHG inventories in place. CityCatalyst is an open-source platform created to close this gap by helping cities build GHG inventories aligned with the international GPC Protocol and receive AI-powered recommendations for mitigation and adaptation actions based on their urban profile, climate risks, and emissions data.
Mirco Rudolph is an AI Applications Engineer at the OpenEarth Foundation, contributing to CityCatalyst, an open-source platform that helps cities build Greenhouse Gas inventories and prioritize climate actions using ML models and LLMs. With a diverse interdisciplinary background in... Read More →
Unlock the secrets to scaling production RAG! This case study dives into our successful deployment of a low-latency RAG chatbot built on Milvus, handling over 10 million vector records. Discover how we managed a 12-18 node Kubernetes cluster powered by cost-effective AWS Graviton CPUs and aggressively used Spot Instances to stay within budget while achieving high accuracy.
Have more than a decade of experience in leading cloud infrastructure of various SaaS applications. Currently serving as an Engineering Manager in software consultancy firm.
Docling, an open source package, is rapidly becoming the de facto standard for document parsing and export in the Python community. Earning close to 30,000 GitHub in less than one year and now part of the Linux AI & Data Foundation. Docling is redefining document AI with its ease and speed of use. In this session, we’ll introduce Docling and its features, including how:
Dr. Michele Dolfi is a technical lead in the AI for Knowledge group at IBM Research, focusing on knowledge engineering and understanding. Michele is one of the researchers who created the Deep Search platform and the Docling open source project. His expertise spans from artificial... Read More →
Phd in theoretical physics, interested in AI, high performance computing and document processing. Chair of the technical steering committee of Docling.
Thursday August 28, 2025 14:45 - 15:10 CEST Emerald Room
Managing and deploying AI models can often require extensive system configuration and complex software dependencies. RamaLama, a new open-source tool, aims to make working with AI models straightforward by leveraging container technology, making the process "boring"—predictable, reliable, and easy to manage. RamaLama integrates with container engines like Podman and Docker to deploy AI models within containers, eliminating the need for manual configuration and ensuring optimal setup for both CPU and GPU systems.
Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. The scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods.
Passionate about AI/ML space and keen to adopt new technologies for solving real-world problems. The work focus these days is on generative AI. Along with the team, we help customers incorporate AI into software engineering.
Trallie is an open-source framework backed by the NGI Search Consortium that leverages the power of large language models (LLMs) to reimagine information extraction (IE) with or without user guidelines. Instead of relying on labelled examples or copious amounts of training on your data collection, Trallie requires very few or no representative examples of the data to convert into a structured format. It has three core objectives:
Cristiano is a Theoretical Physicist with a PhD in Quantum Information Theory from SISSA, Italy. With 10 years of experience in Deep Learning and AI, he is currently the Lead AI Scientist at Pi School and Tech Lead of two ESA grants. He is a lecturer in Deep Learning at the MHPC (ICTP/SISSA... Read More →
Vijayasri Iyer is a Machine Learning Scientist at Pi School, where she has led multiple international teams in developing Generative AI solutions. She holds a Bachelor’s degree in IT, Master’s in AI and certifications in Technology Policy and AI Safety.
Generative AI workloads have introduced a new class of infrastructure challenges—massive model sizes, unpredictable bursty inference, tight latency budgets, and soaring GPU costs. While teams invest heavily in model compression and distillation, they often overlook the other half of the equation: the ML pipeline.
Shashidhar Shenoy is a software engineer and technical leader specializing in distributed systems, AI/ML infrastructure, and scalable authentication platforms. With over a decade of experience, he has led high-impact projects, including optimizing cloud infrastructure for AI/ML workloads... Read More →
As a Sr. Machine Learning Engineer at Torc Robotics, I am building critical ML infrastructure for the L4 self-driving class-8 trucks, paving the way for safer transportation of freight.
Machine Learning Engineering Leader with 8+ years of experience architecting production ML systems across e-commerce, hospitality, and online betting. Expert in semantic search, recommendation engines, AI agents, and MLOps. Scaled ML team in company while maintaining hands-on involvement... Read More →
Thursday August 28, 2025 15:40 - 16:05 CEST Emerald Room
Model startup latency is a persistent bottleneck for modern inference workloads, particularly when using custom kernels written in Triton that are Just In Time (JIT) compiled. In this talk, we’ll present a novel approach to speeding up model boot times by wrapping Triton kernel caches in OCI container images.
Maryam is a Principal Engineer on the Emerging Tech team in the Office of the CTO at Red Hat. Her research is focused on Networking and Sustainability. She's contributed to and led several OpenSource projects. She has been working on AF_XDP and preparing it for cloud native use cases... Read More →
Alessandro Sangiorgi is a Software Engineer in the Emerging Technologies Group within the Office of the CTO at Red Hat. He has extensive experience across Cloud, Distributed Systems, AI, and Networking products and technologies.
Thursday August 28, 2025 15:40 - 16:05 CEST G001-002
In this 1-hour workshop, participants will have the opportunity to learn how to achieve robust observability for Large Language Models (LLMs) while safeguarding sensitive data. As LLMs become integral to production systems, monitoring their performance, usage, and costs is essential, and so is protecting user privacy! This session addresses these challenges using open-source tools such as OpenTelemetry + OpenLIT, and Prometheus + Grafana.
Joaquin Rodriguez, a Senior Software Engineer in the Industry Solutions Engineering organization at Microsoft, helps customers tackle their toughest technical problems, on the cloud and at the edge. With over ten years of experience, Joaquin is passionate about open-source technologies... Read More →
In our talk, we present a practical use-case within the 8RA (https://www.8ra.com/) program, the IPCEI covering Cloud and Infrastructure Services (CIS), built on top open-source software. Our use-case exploits both ML and GenAI to support scenarios within Multi-Provider Cloud Edge Continuum, cloud infrastructure federation, automated service request and allocation of applications to edge sites properly selected. We design an architecture whose core is a set of AI agents, which collaborate to accomplish different tasks, ranging from application deployment file generation up to site prediction for application deployment, according to service requests taken as input by users in natural language. Specifically, our architecture currently includes several agents: LANE (Language-to-Action Neural Engine), responsible for processing user requests expressed in natural Language; Placement, providing the optimal edge site recommendation for each application, ensuring maximum energy efficiency once deployed. It leverages an AI-driven approach to predict energy consumption and optimize resource allocation, improving the sustainability of cloud services.
I am a technical leader with a passion for technology and education. I currently help people learn HashiCorp products. Previously, I built engaging, interactive tutorials for Terraform and Packer, and managed the Consul Education team. I also advise DreamsForSchools in designing computer... Read More →
Thursday August 28, 2025 16:15 - 16:40 CEST Emerald Room
RAG pipelines are everywhere—but most are barely holding together. As GenAI moves from demos to production, the cracks are showing: silent failures, hallucinations, and a total lack of insight into what your AI is actually doing.
Alison Cossette is a Developer Advocate at Neo4j, specializing in Graph Data Science. She blends deep technical expertise with a passion for responsible AI, advocating for transparency and ethical practices in GenAI. A podcast host and educator, she bridges data science and real-world... Read More →
This session will explore how Elyra, an open source project that extends the JupyterLab user interface to simplify the development of data science and AI models, empowers data scientists and ML engineers to build, automate, and optimize end-to-end AI/ML pipelines with ease. We’ll demonstrate how Elyra’s visual pipeline editor simplifies workflow orchestration while integrating seamlessly with Kubeflow, other MLOps tools.
Ritesh Shah is a Senior Principal Architect with Red Hat and focuses on creating and using next-generation platforms, including AI/ML workloads as well as application modernisation and deployment.
Thursday August 28, 2025 16:15 - 16:40 CEST G001-002
Retrieval Augmented Generation (RAG) systems are quickly becoming the backbone of enterprise GenAI applications, but they introduce unique security risks that most teams overlook. In this hands-on session, I'll demonstrate real vulnerabilities I've discovered in production RAG systems and show you exactly how to fix them. We'll start by breaking things - I'll perform live attacks including:
I am Site Reliability Engineer at KodeKloud . I am an Open source contributor, evaluating and contributed in various open source tools and projects, such as, Microsoft's Open source libraries, OpenCV, SUSE, etc. I was also a Google Summer of Code contributor 2022 and a GitHub Extern... Read More →
Building a protocol-based server from scratch is never just about code—it’s about discovery, mistakes, iteration, and ultimately, crafting something meaningful from raw ideas. In this talk, we’ll share the behind-the-scenes story of how we at Hud built our first MCP (Message-Client-Protocol) server—what MCP is (and what it’s not), why we needed it, and how we got from an idea to a working production system.
May Walter is a software engineer, researcher, entrepreneur and serial CTO. She is currently co-founder and CTO of Hud, a startup company still in stealth. Before Hud she was a founding team member and CTO at Santa, and prior to that CTO at Bond (acquired by REEF Technology), where... Read More →
Thursday August 28, 2025 16:50 - 17:15 CEST Emerald Room
Join us for a deep dive into architecting and implementing a scalable LLM inference service on Amazon EKS as the foundation for workload orchestrating, while incorporating NVIDIA NIMS for optimal GPU utilization, LangChain for flexible LLM operations, Milvus for efficient vector storage, FluxCD for GitOps-driven deployments, Karpenter for horizontal scaling and Prometheus and Grafana for Observability.
Riccardo Freschi is a Sr. Solutions Architect at AWS, focusing on Application Modernization. He works closely with partners and customers, to help them transform their IT landscapes in their journey to the AWS Cloud, by refactoring existing applications and building new ones, cloud... Read More →
Thursday August 28, 2025 16:50 - 17:15 CEST G001-002
With the rise of on-device intelligence, the push to run LLMs on edge hardware — phones, Raspberry Pis, even microcontrollers — is accelerating. At the heart of this revolution is quantization: the art of shrinking models without shrinking their intelligence.
I'm Aditi Gupta, a Software Developer Engineer. Graduated from Asia's largest tech university for women, Indira Gandhi Delhi Technical University,I've been deeply immersed in cloud-native technologies and AI/ML advancements. Skilled in containerisation, micro-service architecture... Read More →
Hi, I am Nikunj Goyal, working as a developer at Adobe and a Maths major from IIT Roorkee. I am working with AI and Machine Learning for some time mainly with Generative AI and graph based methods. I am a core part of Text-to-vector generation team at my org and previously worked... Read More →
