Software Engineer Decentralized and Confidential Learning on Structure Data

Job description

This research project focuses on federated learning (FL), an emerging decentralized learning paradigm that features privacy protection by design. Under FL, machine learning models (e.g., LightGBM) and deep models can be learned directly at the data premise, without centralized data collection. The main focus is on tabular data and time series data due to their dominant presence in industries.

The research objective of this PhD project is to derive scalable decentralized machine learning algorithms for tabular data.

The key tasks of this project are:

• Designing privacy-preserving data exchanging strategies
• Deriving vertical and horizontal federated learning for tabular and time series data
• Deriving generative models for tabular data (e.g., generative adversarial networks)
• Designing decentralized training frameworks for tabular and time series data synthesizers

Job requirements

We are looking for candidates who satisfy the following requirements: an MSc degree with excellent results in Computer Science, preferably in distributed systems, theory, or related areas.

• MSc degree in Computer Science (preferably in distributed systems, theory, or related areas) with excellent results
• 0–3 years of relevant experience
• Experience in writing python and conducting scientific evaluations through experimentation
• Profound knowledge in deep machine learning algorithms and time series models
• Experience in designing and developing large scale distributed learning systems

Only candidates from EU countries or with a Dutch work permit are eligible for this vacancy (due to Dutch regulations).

TU Delft (Delft University of Technology)

Delft University of Technology is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society.

Faculty of Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. The faculty develops sustainable and future-proof technologies, including AI, and provides an innovative research environment with excellent labs and facilities. In total, more than 1000 employees and 4,000 students work and study in this innovative environment.

Conditions of employment

• Duration of contract is 2 years (temporary)
• An excellent pension scheme via the ABP
• The possibility to compile an individual employment package every year
• Discount with health insurers on supplemental packages
• Flexible working week
• Every year, 232 leave hours (at 38 hours). You can also sell or buy additional leave hours via the individual choice budget
• Plenty of opportunities for education, training and courses
• Partially paid parental leave
• Attention for working healthy and energetically with the vitality program