Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Inria Villeneuve d'Ascq invites applications for a postdoctoral position in sequential learning and two-player imperfect information games. The candidate will study how different structures influence learning, derive statistical characterisations, and design efficient algorithms, with opportunities to collaborate on robust, privacy-aware, unbiased sequential decision making.
The role involves bibliographic research, idea generation, presenting at seminars, and publishing in leading venues.
In his/her journey of postdoc, the candidate will be supported by ANR JCJC project REPUBLIC and PEPR Foundry, and supervised by Debabrota Basu. Debabrota is affiliated with the Scool project-team (previously SequeL) of Inria Centre at University of Lille. As a team, Scool is internationally recognised for developing theories and algorithms for sequential learning and decision making, i.e. in the fields of bandits and reinforcement learning.
The candidate is expected to work on understanding impact of different types of structures on learning is sequential two-player games.
The project is expected to simulate the existing and new collaborations with researchers and groups working on responsible AI, bandits, and reinforcement learning. The candidate will also be part of the HumAIn alliance that aims toward studying humane impact of deploying AI.
From the application point of view, Scool is involved in multiple projects that incorporates medical data, agricultural data, and e-commerce. Depending on the future development, we will be interested to deploy such responsible AI systems and algorithms for securing such applications.
To be specific, the postdoc will first investigate the fundamental question of impact of structures and constraints on imperfect information two-player games. The goal is to derive statistical characterisations and design efficient algorithms, when possible. The candidate can work in tandem with the PhDs working in the group on the related topic to develop constrained RL formulations for robustness, privacy, and unbiasedness sequential decision making and adaptive testing. For further details, please contact Debabrota by email.
All research activities, that is bibliographical search, proposing original ideas related to the topic and developing them, presenting the work in the Scool seminar, workshops and conferences. Writing papers in order to get them accepted in the best conferences and journals of our field of research (e.g. ICML, NeurIPS, COLT, IJCAI, AAAI, JMLR). Since the work involves and impacts the responsible AI in general, the successful candidate should collaborate in writing scientific articles aiming towards the larger audience.
The candidate should preferably have the following skills:
The deadline of application is 15th November, 2026.