Open positions
We are looking for talented interns, PhD students and
post-docs! Here are our current open offers:
Type: Internship
Duration: 4 to 6 months
Description:
The goal of this internship is to improve the attack capacities of PyRAT to detect weakness in the model either by increasing the strength of the adversarial attacks used or by using additional information gathered from the analysis of PyRAT. Additionally, as finding attacks can be time consuming...
Type: Internship
Duration: 4 to 6 months
Description:
The aim of this internship is to study the applicability of variable substitutions to accelerate SMT solvers on neural network formal verification. To do so, the intern will use the CAISAR open-source platform to manipulate the neural networks control flow as logical formulaes. A suggested SMT so...
Type: Internship
Duration: 4 to 6 months
Description:
The concept of a confidence-based safety property has been recently introduced by Athavale et al. (Athavale et al. 2024) to recast robustness and fairness properties in terms of the confidence score with which a neural network generates its outcomes. The main objective of this internship will be ...
Type: Internship
Duration: 4 to 6 months
Description:
The first half of the internship will be dedicated towards developing methods for building a fast iterative and sound solver with linear objective function subject to non-linear constraints.The second half of the internship will consist of implementing the aforementioned solver with quadratic con...
Type: Internship
Duration: 4 to 6 months
Description:
During this internship, you will study the use of AISER’s OOD-detection method, PARTICUL, to identify whether new inputs were tampered with. You will work using the open-source library CaBRNet(Xu-Darme et al. 2024), developped at CEA LIST, which provides an implementation of PARTICUL.
Type: Internship
Duration: 4 to 6 months
Description:
This internship focuses on the use of machine learning models for the recognition and classification of bird songs. Audio clips are often encoded in the form of spectrograms, i.e. 2D representations of the intensity of the signal at various frequencies, across a given period of time. Since specto...
Type: Internship
Duration: 4 to 6 months
Description:
In this internship, we propose to use generative AI to de-activate pixels in a more subtle way - creating images that resemble the original one but with missing features while remaining “in distribution” - and to study the impact of such method on the evaluation of the correctness of XAI methods.
If you think you will be a fit for our team but don’t find a
specific offer, you can also reach out for a spontaneous
application. We will gladly consider those as well.
Application modalities
Our field is at the crossroads of formal verification and artificial
intelligence.
As it is not realistic to be expert in both fields, we encourage candidates that do not meet the full qualification requirements to apply nonetheless.
The candidate will be monitored by at least two research engineers of the team.
If you are interested in this internship, please send by email to one of the person listed on the contact page an application containing:
- your resume;
- a cover letter indicating how your curriculum and experience match the qualifications expected, and how you would plan to contribute to the project;
- at least your bachelor and master 1 transcripts;
- the contact details of two persons (at least one academic) who can be contacted to provide references.
Applications are welcomed until the position is filled. Please note that the administrative processing may take up to 3 months, so we strongly encourage you to apply diligently and answer as quickly as possible when prompted with administrative documents.