Data Scientist / AI Engineer

Ayoub El Majjodi

Based
Bergen, Norway · UTC+1
Focus
LLMs · Agentic AI · Search & Retrieval · Evaluation & Benchmarking
Now
Real-estate search & discovery @ Zrch

I build search, recommendation, and personalization systems, currently focused on ranking and discovery in the real estate domain, and on LLM- and agent-based systems that make search and recommendations more helpful.

Previously a PhD researcher in recommender systems and behavioral data science at the University of Bergen, studying how personalization shapes decisions and encourages healthier behavior.

Ayoub El Majjodi

I'm a Data Scientist and AI Engineer with a PhD in Information Science from MediaFutures and the University of Bergen. I'm passionate about AI systems that bridge research and real-world applications. My interests span LLMs, search, personalization, retrieval, and agentic AI, with a focus on evaluation, benchmarking, and scalable AI engineering.

I enjoy working at the intersection of AI, engineering, and product, collaborating across disciplines to build reliable AI-powered experiences. Today that means LLM-based property understanding, agentic search and discovery workflows, and rigorous benchmarking of embedding models, retrieval strategies, and LLMs in the real estate domain.

My PhD was supervised by Prof. Christoph Trattner and Assoc. Prof. Alain D. Starke, within the Behavioral Data Analytics & Recommender Systems group and Work Package 2, User Modeling, Personalization & Engagement, at MediaFutures. It explored how personalization and recommender systems influence decision-making and promote healthier behavior across the food and news domains.

Data Scientist Feb 2026 — Present Zrch · Bergen, Norway

Build and evaluate AI capabilities for search, discovery, and personalization that improve relevance and engagement in the real estate domain. Design agentic search and retrieval workflows (LangGraph, LangSmith); run systematic benchmarking of embedding models, retrieval strategies, LLMs, and document-parsing pipelines; and partner with product and design to define, prototype, and validate AI features across several initiatives.

Selected project

Smart Search, a natural-language search experience for dinbostad.se. Users describe what they are looking for in plain text; the system infers intent with LLMs and returns relevant listings. Scope spanned LLM selection, prompt engineering, retrieval design, and end-to-end evaluation and benchmarking of the pipeline.

PhD Research Fellow — Recommender Systems & Digital Nudges 2021 — 2025 MediaFutures, University of Bergen · Norway

Recommender systems, user modeling, and behavioral interventions across the food and news domains; offline and online evaluation of personalization.

Teaching Assistant — Research Topics in Recommender Systems 2022 — 2025 University of Bergen · Norway
Research Intern — ML & Recommender Systems Sep — Dec 2024 University of Bari · Italy
Research Assistant — Cloud Computing (Unikernels) 2020 — 2021 Tampere University · Finland
PhD, Information Science — Recommender Systems 2021 — 2025 University of Bergen (UiB) · Norway
MSc, Data Science & Big Data 2017 — 2019 ENSIAS · Morocco
BSc, Mathematics & Computer Science 2016 — 2019 Ibn Zohr University · Morocco
Focus
LLMs Agentic AI Search & Retrieval Recommender Systems Personalization Evaluation & Benchmarking
Generative AI
Retrieval-Augmented Generation Agentic Workflows Prompt Engineering LLM & Agent Evaluation Embedding & Retrieval Benchmarking Observability & Tracing
Machine Learning
Learning to Rank Recommendation Models Computer Vision User Modeling Experimentation & A/B Testing
Tools
Python LangGraph LangSmith LangChain Hugging Face scikit-learn AWS SQL Git / GitLab
Best Poster Award 2024 SFI MediaFutures Annual Conference
Generative AI with Large Language Models 2025 Amazon Web Services · DeepLearning.AI
AI Agents Fundamentals 2025 Hugging Face
LangGraph Essentials 2024 LangChain — Agentic AI, LangGraph
Introduction to Food & Health 2023 Stanford Online (Coursera)
Deep Learning Specialization 2018 DeepLearning.AI
Program Committee 2024, 2025 ACM Conference on User Modeling, Adaptation and Personalization (UMAP)

Reviewing full and short papers on recommender systems, personalization, and user modeling.

Proceedings & Video Co-chair 2024 ACM Conference on Recommender Systems (RecSys)

Coordinated the camera-ready proceedings and the conference video program with authors and publishers.

Student Volunteer 2023, 2024 ACM RecSys Summer School · Singapore, Bari (Italy)

Supported organisation, sessions, and participants at the ACM Recommender Systems Summer School.

Location Bergen, Norway