Data Scientist (TE-DPS-AIM-2026-75-GRAP) at CERN

Do you want to apply your Data Science and AI expertise to one of the world's most complex scientific and engineering environments? Join CERN and take a leading role in developing an AI driven prescriptive maintenance and operational assistance platform for the Large Hadron Collider (LHC). In this position, you will drive the full lifecycle of an innovative AI solution designed to improve the reliability and performance of accelerator systems. Your work will span requirements gathering, data preparation, model development and lifecycle management, integration of safety considerations, creation of AI-assisted diagnostics tools, and the implementation of robust data and API pipelines. You will develop a proof of concept using LHC Run 3 data, then lead testing and validation on representative systems within the TE Department, with the goal of achieving full deployment for Run 4. Your contribution will enable CERN to harness advanced AI methods to reduce unplanned downtime, strengthen operational resilience, and support data-driven decision making across critical accelerator infrastructure. Your responsibilities • Collect and formalise operational use cases and user stories with engineers and maintenance experts; translate them into functional and technical specifications. • Define system requirements and draft solution architecture for an AI-driven prescriptive maintenance platform. • Design and implement scalable data pipelines for ingesting and processing operational data (e.g. time series, logs, equipment metadata, technical documentation) using distributed processing frameworks. • Perform data pre-processing, feature engineering, and exploratory analysis to prepare datasets for modelling. • Design and execute machine learning experiments for anomaly detection, failure prediction, and prescriptive recommendations. • Implement experiment tracking, model validation, and reproducibility practices using ML lifecycle management tools (e.g. MLflow or similar). • Package and deploy models into production environments through APIs and containerised services (e.g. Podman), supporting orchestration platforms such as Kubernetes. • Contribute to system integration, testing, performance monitoring, and iterative improvement of deployed models. • Produce clear technical documentation, specifications, and user-oriented material to ensure maintainability and knowledge transfer. • This role includes team supervision responsibilities.Your profile • Academic background in Data Science, Computer Science, Engineering, Applied Mathematics, or a related quantitative field. • Experience working on applied machine learning or data-driven projects addressing real-world operational or engineering problems. • Experience with version control systems (e.g. Git) and collaborative development workflows.Skills • Proficiency in Python for data analysis and machine learning (e.g. NumPy, pandas, scikit-learn, PyTorch or similar frameworks). • Understanding of machine learning techniques relevant to time series analysis, anomaly detection, and predictive modelling. • Knowledge of data pre-processing, feature engineering, and exploratory data analysis (EDA). • Familiarity with distributed data processing tools (e.g. Apache Spark) or similar big data frameworks. • Good knowledge of experiment tracking and ML lifecycle management tools (e.g. MLflow or equivalent). • Understanding of REST APIs and model serving concepts. • Familiarity with containerisation technologies (e.g. Podman) and basic concepts of orchestration platforms (e.g. Kubernetes). • Ability to write structured technical documentation and maintain reproducible code. • Ability to structure complex, ambiguous problems into well-defined analytical approaches. • Spoken and written English, with a commitment to learn French.Eligibility criteria: • You are a national of a CERN Member or Associate Member State. • You have a professional background in Data Science, Computer Science, Mathematics (or a related field) and have either: • a Master's degree with 2 to 6 years of post-graduation professional experience; • or a PhD with no more than 3 years of post-graduation professional experience. • You have never had a CERN fellow or graduate contract before.