Applied Physicist

Job Posting Organization:
CERN, the European Organization for Nuclear Research, is at the forefront of scientific research and technological advancement. Established in 1954, CERN has grown to become one of the world's largest and most respected centers for scientific research, employing thousands of professionals from diverse fields including physics, engineering, and administration. The organization operates in multiple countries and is known for its collaborative approach to solving complex scientific challenges. CERN's mission is to push the boundaries of knowledge and technology, fostering an environment where innovation thrives and diverse perspectives are valued. Diversity has been a core value since its inception, and it remains central to CERN's ongoing success and mission.

Job Overview:
The position of Applied Physicist at CERN involves contributing to the development of machine learning-based Particle-Flow reconstruction for the CMS experiment. This role is critical as it integrates advanced algorithms into the High Level Trigger as part of the Next Generation Trigger project, where timing constraints and real-time performance are paramount. The successful candidate will also extend these methodologies to future collider experiments such as FCC-ee, focusing on optimizing reconstruction performance, evaluating detector-specific strategies, and applying cutting-edge machine learning techniques to enhance physics precision. The role requires a deep understanding of high energy physics and the ability to work with complex data and algorithms to achieve significant advancements in experimental physics.

Duties and Responsibilities:
The responsibilities of the Applied Physicist include developing machine learning-based Particle Flow components using TICL inputs in the CMS experiment and validating their performance against standard PF and TICL metrics. The candidate must ensure robustness, interpretability, and debuggability of the algorithms in realistic CMS environments. Additionally, they will explore the applicability of these approaches for future collider detectors, leveraging the FCC framework and the Key4hep ecosystem. Leading ML-based reconstruction studies for CLD and extending the approach to other detector concepts such as ALLEGRO, IDEA, and GRAiNITA is also part of the role. The physicist will design suitable data representations for heterogeneous detector inputs, handle large-scale graphs and distributed training, and benchmark performance on physics observables and reconstruction metrics.

Required Qualifications:
Candidates must demonstrate proficiency in developing and training machine learning models specifically targeting high energy physics reconstruction, particularly for complex objects like Particle Flow candidates. A deep understanding of High Energy Physics (HEP) Reconstruction Code is essential, showcasing the ability to comprehend, manage, and author reconstruction code tailored for HEP experiments. Solid knowledge of detector systems and particle-detector interactions is required for the development of Particle Flow algorithms. Strong programming skills in Python and C++ are necessary, with Python being used for scripting and tooling, while C++ is essential for developing efficient algorithms and integrating machine learning into the HEP framework for fast inference. Familiarity with CMSSW and FCCSW is considered a plus.

Educational Background:
The ideal candidate should possess a professional background in Computer Science, Physics, or a related field. A Master's degree with 2 to 6 years of post-graduation professional experience is required, or alternatively, a PhD with no more than 3 years of post-graduation professional experience. It is important that candidates have not previously held a CERN fellow or graduate contract.

Experience:
Candidates should have a significant level of experience in high energy physics, particularly in the development and training of machine learning models for reconstruction tasks. Experience in advanced machine learning model creation, large scale and distributed training, and deployment is crucial, as the role involves integrating AI-driven techniques into reconstruction algorithms. A strong foundation in programming and familiarity with high energy physics experiments is also necessary.

Languages:
Fluency in spoken and written English is mandatory, and candidates should be committed to learning French as part of their professional development.

Additional Notes:
The contract duration for this position is 24 months, with the possibility of extension up to a maximum of 36 months. The working hours are set at 40 hours per week, and the job offers hybrid flexibility. The target start date for this position is 01-March-202

• The job reference is EP-CMG-DS-2026-8-GRAP, and it falls under the field of Experimental Physics. The compensation includes a monthly stipend between 6287-6911 Swiss Francs (tax-free), 30 days of paid leave per year plus 2 weeks of annual closure, comprehensive health insurance coverage, family allowances, a relocation package, and opportunities for on-the-job and formal training including language classes.