Data Scientist for AI-driven Maintenance Platform

Job Posting Organization:
CERN, the European Organization for Nuclear Research, was established in 1954 and is one of the world's largest and most respected centers for scientific research. With over 2,500 employees and thousands of scientists from around the globe, CERN operates in multiple countries, focusing on understanding the fundamental structure of the universe. The organization is renowned for its groundbreaking work in particle physics and technology, fostering an environment of innovation and collaboration among a diverse range of professionals.

Job Overview:
In this role, you will leverage your expertise in Data Science and AI to develop an innovative AI-driven prescriptive maintenance and operational assistance platform specifically for the Large Hadron Collider (LHC). Your responsibilities will encompass the entire lifecycle of the AI solution, from gathering requirements and preparing data to developing models and managing their lifecycle. You will also integrate safety considerations, create AI-assisted diagnostic tools, and implement robust data and API pipelines. The position involves developing a proof of concept using LHC Run 3 data, leading testing and validation on representative systems within the TE Department, and ultimately achieving full deployment for Run

• Your contributions will be pivotal in enabling CERN to utilize advanced AI methods to minimize unplanned downtime, enhance operational resilience, and support data-driven decision-making across critical accelerator infrastructure.

Duties and Responsibilities:
Your primary responsibilities will include collecting and formalizing operational use cases and user stories in collaboration with engineers and maintenance experts, translating these into functional and technical specifications. You will define system requirements and draft the solution architecture for the AI-driven prescriptive maintenance platform. Additionally, you will design and implement scalable data pipelines for processing operational data, perform data pre-processing and exploratory analysis, and execute machine learning experiments focused on anomaly detection and failure prediction. You will also implement practices for experiment tracking and model validation, package and deploy models into production environments, contribute to system integration and performance monitoring, and produce clear technical documentation to ensure maintainability and knowledge transfer. This role will also involve supervising team members.

Required Qualifications:
Candidates must possess an academic background in Data Science, Computer Science, Engineering, Applied Mathematics, or a related quantitative field. Experience in applied machine learning or data-driven projects addressing real-world operational or engineering challenges is essential. Familiarity with version control systems and collaborative development workflows is also required. Proficiency in Python for data analysis and machine learning, understanding of machine learning techniques relevant to time series analysis, and knowledge of data pre-processing and exploratory data analysis are crucial. Familiarity with distributed data processing tools and ML lifecycle management tools is expected, along with an understanding of REST APIs and containerization technologies.

Educational Background:
The ideal candidate should have 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 in a relevant field such as Data Science, Computer Science, or Mathematics. Candidates must also be nationals of a CERN Member or Associate Member State and should not have previously held a CERN fellow or graduate contract.

Experience:
The position requires a professional background in Data Science or a related field, with a minimum of 2 years of relevant experience for Master's degree holders or up to 3 years for PhD holders. Experience should include applied machine learning or data-driven projects that address real-world operational or engineering problems, demonstrating the ability to work effectively in a collaborative environment.

Languages:
Fluency in spoken and written English is mandatory, and candidates should demonstrate a commitment to learning French, which is considered an asset for the role.

Additional Notes:
The contract duration is 24 months, with the possibility of extension up to a maximum of 36 months. The position is fully onsite, requiring a commitment of 40 hours per week. The target start date for this position is June 1, 202

• The job reference is TE-DPS-AIM-2026-75-GRAP, and it falls under the field of Data Science & Data Analytics. The compensation includes a monthly stipend between 6372-7004 Swiss Francs, 30 days of paid leave per year, comprehensive health insurance coverage, family allowances, a relocation package, and opportunities for on-the-job and formal training, including language classes.