Researcher with PhD in the area of Privacy Preserving Data Processing
Role overview
# Researcher with PhD in the area of Privacy Preserving Data Processing
## Scope and purpose of the position The purpose of this position is to support research and development (R&D) activities focused on designing novel solutions for privacy-preserving machine learning, with a particular focus on Large Language Models (LLMs). The selected candidate will contribute to the design and implementation of privacy-enhancing technologies tailored to transformer-based architectures. This role involves close collaboration with interdisciplinary teams, including academic researchers, software engineers, and industry partners, to help translate cutting-edge research into practical solutions for privacy-preserving inference and fine-tuning of LLMs.
## Responsibilities and activities - The selected candidate will join research groups focused on the development of privacy-preserving data-driven solutions, with specific focus on privacy-enhancing technologies and privacy-preserving machine learning technologies. - Contribute to the design and implementation of privacy-preserving technologies, specifically tailored to transformer-based architectures and LLMs, with emphasis on secure training and inference. - Collaborate with interdisciplinary teams, including NLP experts, software engineers, and academic/industrial partners, to translate cutting-edge research into practical applications. - Support research and development activities aimed at advancing privacy-preserving machine learning techniques, evaluating their effectiveness, scalability, and compliance. - Develop and test software prototypes of privacy-preserving systems, contributing to the integration of the proposed solutions into real platforms or technological demonstrators.
Key requirements
- PhD in Computer Science, Data Science, Machine Learning, or related fields.
- Proven experience with privacy-enhancing technologies and their application to privacy-preserving machine learning.
- Strong experience with deep learning frameworks (e.g., PyTorch, TensorFlow) and data science tools (e.g., NumPy, Pandas, Scikit-learn).
- Proficient in programming, especially in Python, with familiarity in version control systems (e.g., Git).
- Solid mathematical background, including linear algebra, probability theory, optimization, and cryptography.
- In-depth understanding of machine learning algorithms, with a focus on transformer-based models.
- Ability to work independently and manage project timelines and deliverables.
- Strong publication record in fields such as privacy, machine learning, and/or natural language processing.