R&D Intern - Fairness in Deep Learning

About the role

This research internship focuses on developing methods to ensure neural network predictions remain independent of continuous sensitive variables like age or income. The intern will implement existing bias-reduction techniques and design new approaches to mitigate discriminatory biases in machine learning models. The role is based at the Artefact research center in Paris.

Responsibilities

• Implement existing bias-reduction methods based on dependency measures.
• Establish a robust protocol to compare different fairness-aware models.
• Analyze the trade-off between model performance and fairness.
• Design and experiment with new bias-reduction methods for continuous variables.
• Utilize open-source libraries to ensure code reproducibility.

Required skills

• Machine Learning
• Deep Learning
• Mathematics
• Statistics
• PyTorch
• scikit-learn

Qualifications

• Master's degree in Applied Mathematics, Statistics, or Machine Learning
• Currently enrolled in a university or engineering school

About the Company

Artefact is an international data services company specializing in data transformation consulting. With 2500 employees, the firm bridges the gap between data and business to deliver tangible results through AI innovation and agile methodologies.