CERN Deep Learning Developer

Big Science Sweden; Genf; Hybrid; CHF 90.000 - 120.000; Vollzeit

Zusammenfassung

CERN IT-CE group is exploring the development of a foundation model tailored to particle physics, capable of interpreting particle behavior in HEP detectors and supporting experimental data processing.

The role involves designing and training transformer-based architectures using calorimeter data, exploring self-supervised learning for multi-task capabilities, and optimizing for computational efficiency. Availability is immediate.

Qualifikationen

• Master's degree with 2–6 years of professional experience since graduation or a PhD with up to 3 years of experience
• You are a national of a CERN Member State or Associate Member State; certain national exclusions apply
• No prior CERN fellow or graduate contract
• Eligibility criteria specified for this position

Aufgaben

• Design and train transformer-based architectures using calorimeter data from collider experiments
• Explore self-supervised learning to enable multi-task capabilities
• Optimize for computational efficiency in model training and inference

Kenntnisse

Deep Learning

Transformer models

Scientific data

Ausbildung

Master's degree in CS or related field

PhD in CS or related field

Tools

Transformer architectures

Jobbeschreibung

Foundation models represent one of the most powerful and promising advancements in Deep Learning, and their application to scientific domains is a rapidly evolving area of research.

At CERN’s IT-CE group, we are exploring the development of a foundation model tailored to particle physics: one capable of interpreting the behavior of particles within High Energy Physics (HEP) detectors and supporting a wide range of tasks relevant to experimental data processing.

This work is carried out in close collaboration with a multidisciplinary team of experts from leading institutes across Europe in the context of TURING, a EC funded project .

As a successful candidate, you will contribute to the design and training of transformer-based architectures using data from calorimeters, specialised detectors that measure particle energy in collider experiments.

Your work will involve investigating methodologies such as self-supervised learning to enable multi-task capabilities, while optimising for computational efficiency.

We are looking for candidates with a strong background in Computer Science or a closely related field. Experience with Deep Learning, transformer models, or scientific data is highly desirable. This position is available immediately.

Be sure to meet the eligibility criteria

• You are a national of a CERN Member State or Associate Member State. Currently, we cannot consider applications from Pakistani, Lithuanian, Latvian, Cypriot and Croatian nationals, as the ceiling defined under Article II.5 of the Associate Membership Agreement has been reached.
• By the application deadline, you have a master’s degree with 2 to 6 years of professional experience since graduation or a PhD with a maximum of 3 years of professional experience since graduation. You are not eligible with only a bachelor’s degree.
• You have never had a CERN fellow or graduate contract before.
• Please pay attention to the additional criteria and requirements for this specific position and mentioned above.