Doctoral position (PhD) on automated maintenance of machine-learning enabled systems

SnT is a leading international research and innovation centre in secure, reliable and trustworthy ICT systems and services. We play an instrumental role in Luxembourg by fueling innovation through research partnerships with industry, boosting R&D investments leading to economic growth, and attracting highly qualified talent.

As the successful candidate, you will join the Security, Reasoning and Validation (SeRVal) group of the SnT, under the supervision of Prof. Yves Le Traon and Dr. Maxime Cordy.

Machine Learning (ML) provides engineers with the prospect of producing data-driven software, with little manual code writing. We are at a turning point in the software industry, as key functionalities are no longer programmed in “the old fashioned way” but implemented by training ML models with data that reflect the expected system behaviour. This radical change offers a unique opportunity to further automate software production, subject to the condition that we can automatically maintain this combination of conventional code with ML models by developing accurate and actionable diagnosis and software update methods. One of the obstacle for adoption of machine-learning is the maintenance cost of the system after its deployment, hindering the benefit of machine-learning.

The overall research objective is the automation of the corrective maintenance activities for Machine-Learning (ML) enabled systems. Indeed, we ambition to define a clear-eyed and principled methodology to automatically validate and maintain data-intensive software systems, with limited human intervention. The main challenge is coping with the specificity of systems blending conventional code-base with ML components, to (almost) automatically detect, localize and fix the faulty behaviours over time.

We’re looking for people driven by excellence, excited about innovation, and looking to make a difference. If this sounds like you, you’ve come to the right place!