Engineering Beyond the Hype: How Knowledge Sharing Drives Production-Hardened AI and Data Systems
In modern enterprise data and AI engineering, technology moves faster than governance frameworks can adapt. New open-source models, orchestration platforms, and vector paradigms emerge weekly. For…
Beyond Vector Search: Building and Benchmarking Enterprise GraphRAG Architectures
Retrieval-Augmented Generation (RAG) has become the standard pattern for grounding Large Language Models (LLMs) in enterprise domain knowledge. However, standard RAG architectures—relying primarily…
Engineering On-Premise LLM Infrastructure: Architecture, Benchmarking, and Production Realities
By Pierre Hockers - Data scientist For organizations operating under strict regulatory bounds or high security requirements, cloud-based LLM APIs present an operational bottleneck. When data…
Sovereign AI Infrastructure in Europe: an engineering and architectural evaluation
By Pierre Hockers - Data scientist European enterprises evaluating Generative AI face a complex infrastructure decision. While the pressure to adopt Large Language Models (LLMs) is high, operating…
Mastering Sovereign AI & Local LLMs
Don’t Let Your Data Become a Liability: navigating the evolving landscape of data modeling
This article serves as a practical guide to choosing the right architectural blueprint to bridge the gap between chaotic raw data and structured insights.
Sovereign compute at scale: architecting for the Belgian AI Factory Antenna
The Belgian AI Factory Antenna gives SMEs and startups unprecedented access to EuroHPC supercomputers, but it comes with strict access rules and technical trade-offs. Discover how to architect your AI workflows for the EuroHPC landscape in our latest guide.
Pioneering the future of aerial intelligence through advanced 3D digital twins
How do we inspect critical infrastructure safely and efficiently? To tackle this, dive into the combination of aerial platforms with advanced AI to create photorealistic, queryable 3D Digital Twins.
Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach
In this paper, we propose a novel schema-agnostic framework for the automated generation of synthetic evaluation datasets from KGs. Unlike previous approaches, our framework establishes a rigorous, deterministic ground truth to specifically quantify the retriever performance across nine distinct query categories, including multi-hop and aggregation tasks.
Turning an intranet into an AI assistant
Sales and support agents can’t live without it : MAiA turns Proximus’ intranet into realtime knowledge, cutting search time and powering 1.4 million questions since launch.
Bridging the Gap: The "Lab-to-Fab" Protocol for Production-Hardened Data Systems
The primary bottleneck in modern data engineering is not a lack of innovative ideas; it is the friction encountered when transitioning a successful prototype into a production-hardened system. When…
Navigating the AI transition in marketing
IEEE Big Data 2025: the shift from scale to smart
IEEE Big Data 2025 signals a shift to secure, hybrid intelligence. CTO Sabri Skhiri unpacks the engineering reality from the conference: the practical shift to embeddings, the real need for security layers, and the limitations of AI agents in production.
Smarter dispatch of technicians
A telecom provider set out to improve service efficiency by predicting the ideal technician for each job, reducing costly misassignments while boosting customer satisfaction through smarter, data‑driven dispatching.
Evaluation of GraphRAG Strategies for Efficient Information Retrieval
Traditional RAG systems struggle to capture relationships and cross-references between different sources unless explicitly mentioned. This challenge is common in real-world scenarios, where information is often distributed and interlinked, making graphs a more effective representation. Our work provides a technical contribution through a comparative evaluation of retrieval strategies within GraphRAG.
Flight Load Factor Predictions based on Analysis of Ticket Prices and other Factors
The ability to forecast traffic and to size the operation accordingly is a determining factor, for airports. However, to realise its full potential, it needs to be considered as part of a holistic approach, closely linked to airport planning and operations. To ensure airport resources are used efficiently, accurate information about passenger numbers and their effects on the operation is essential. Therefore, this study explores machine learning capabilities enabling predictions of aircraft load factors.
Investigating a Feature Unlearning Bias Mitigation Technique for Cancer-type Bias in AutoPet Dataset
We proposed a feature unlearning technique to reduce cancer-type bias, which improved segmentation accuracy while promoting fairness across sub-groups, even with limited data.
Beyond the hype: how NVIDIA GTC Paris 2025 trends are shaping industry
NVIDIA GTC Paris 2025 revealed an unprecedented scale and breadth of innovation, with a clear focus: not on predicting the future of AI, but on demonstrating how existing technologies are being put to work today. Our CTO Sabri Skhiri was on the ground to bring back insights.
Muppet: A Modular and Constructive Decomposition for Perturbation-based Explanation Methods
The topic of explainable AI has recently received attention driven by a growing awareness of the need for transparent and accountable AI. In this paper, we propose a novel methodology to decompose any state-of-the-art perturbation-based explainability approach into four blocks. In addition, we provide Muppet: an open-source Python library for explainable AI.
Tech insights from GTC Paris 2025
Among the NVIDIA GTC Paris crowd was our CTO Sabri Skhiri, and from quantum computing breakthroughs to the full-stack AI advancements powering industrial digital twins and robotics, there is a lot to share!
The LLM coding revolution needs a rulebook
Teams ship AI-generated code faster than ever — and accumulate debt just as fast. The problem isn't the tools. It's the missing process around them.
From data governance to GenAI: strategic insights from Warsaw Tech Summit 2025
This year, one of the biggest technological conferences in Central Europe changed its name to Data & AI Warsaw Tech Summit to reflect the latest technological advancements. Our CTO Sabri Skhiri was on the ground to bring back insights.
S'épanouir dans son travail avec Maryse Colson, Head of people office chez Euranova
Est-ce qu’il est encore possible de rester 10 ans dans la même entreprise en 2025 ? Dans ce nouvel épisode de Métro, Boulot, Finito, j’accueille Maryse Colson, Head of people office chez Euranova, l’entreprise dans laquelle elle évolue depuis 10 ans...
Development & Evaluation of Automated Tumour Monitoring by Image Registration Based on 3D (PET/CT) Images
Tumor tracking in PET/CT is essential for monitoring cancer progression and guiding treatment strategies. Traditionally, nuclear physicians manually track tumors, focusing on the five largest ones (PERCIST criteria), which is both time-consuming and imprecise. Automated tumor tracking can allow matching of the numerous metastatic lesions across scans, enhancing tumor change monitoring.