Home » Join us » Opportunities


PhD offers

Subject: Physics Based Deep Learning for Modeling Complex Dynamics. Applications to Climate


Deep Learning is beginning to be explored for scientific computing in domains traditionally dominated by physics models (first principles) like earth science, climate science, biological science, etc. It is particularly promising in problems involving processes that are not completely understood, or computationally too complex to solve by running the physics inspired model. The direct use of pure machine learning approaches has however met limited successes for scientific computing. Hence, researchers from different communities have started to explore (i) how to integrate physics knowledge and data, and (ii) how to push the limits of current ML methods and theory; two challenging directions. We consider here deep learning approaches for the modeling of complex dynamical systems characterizing natural phenomena, a recent and fast growing research topic (Willard et al. 2020, Thuerey et al. 2021). Motivating problems and applications will come from climate science (de Bezenac et al. 2018, Ayed et al. 2020).

Scientific Objective:

The global objective is the development of new models leveraging observation or simulation data for the modeling of complex spatio-temporal dynamics characterizing physical phenomena such as those underlying earth-science and climate observations.  The classical modeling tools for such dynamics in physics and applied mathematics rely on partial differential equations (PDE). Despite their successes in different areas, current ML based approaches are notably insufficient for such problems. Using ML for physics raises new challenging problems and requires rethinking fundamental ML ideas.

Research directions:

  • Hybrid systems – Integrating Physics and Deep Learning,
  • Domain generalization for deep learning as dynamical models,
  • Learning at Multiple Scales.

Required Profile: Master in computer science or applied mathematics, Engineering school.  Background and experience in machine learning. Good technical skills in programming.

General information:

  • Thesis director: Patrick Gallinari
  • Thesis co-supervisors: M. Levy and S. Thiria of LOCEAN laboratory
  • Location: ISIR (Institut des Systèmes Intelligents et de Robotique), Campus Pierre et Marie Curie, 4 place Jussieu, 75005 Paris.
  • Start date of the thesis: October / November, 2022
  • The research topic is open and, depending on the candidate’s profile, it may be more theoretically oriented or more application-oriented.

Contact person:

  • Patrick Gallinari
  • Email : patrick.gallinari(at)sorbonne-universite.fr
  • Send your application by email, with [subject of the thesis] in the subject line, a CV, a letter of motivation, the grades obtained in master, and letters of recommendation if possible.

Download this offer

Subject: Computational models to predict user trajectories in dynamic environments


Reaching an object (e.g selecting a 3D object in VR or an icon on the desktop) is one of the most fundamental tasks in Human Computer Interaction (HCI). In HCI, Fitts’ law has been extensively used to predict the pointing time depending on the distance and size of the target (object). It has been used to compare different devices, as well to develop advanced interaction techniques. However, Fitts’ law remains a behavioural model providing little explanation regarding the cognitive processes and thus it does not explain/predict how users adapt their behaviour in dynamic environments e.g., tasks involving external forces or dynamic mappings between physical and virtual movements. A model that would predict human produced trajectories in dynamic environments would inform the design of many non-static input-output mappings (e.g., adaptive mice, VR techniques that manipulate the mapping), by allowing counterfactual reasoning.

Project description:

In this thesis, we wish to provide a comprehensive view of how people produce and adapt their trajectories in a new and/or dynamic environment. We embrace a model-based view of action, where human policy builds on predictions of an internal world model of the task to be accomplished, in line with the optimal control framework pioneered by Todorov. In this classical framework, the internal model is static and identified beforehand. We hypothesise that, rather than being static, this internal model is continually kept up to date, in light of conflicting prediction and sensory information. Modeling and integrating this learning process in the optimal control framework is the open problem that we address. To achieve this, we will adapt Todorov’s classical model, by having the internal model inferred. This inference will be achieved by progressively updating the original outdated internal model, based on an error signal between predicted and observed outcome. The rates of updating (how often the model parameters are updated and by how much) will be determined from empirical data.

Scientific Objective:

The goals of this thesis are:

– adapting Todorov’s optimal control model for aimed movements by adding a learning mechanism that updates the internal world model,

– extending that model with feedforward mechanisms, Todorov’s model being purely feedback driven,

– validating and calibrating the new models on empirical data,

– implementing an interaction technique that leverages the new models (demonstrator).

Required Profile: Applicants with a strong academic record in HCI, a field related to motor control, or control theory are encouraged to apply.

Required skills: Interest and/or experience in computational user modeling is required. The ability to conduct controlled experiments, as well as the ability to design VR interactions is appreciated.


General information:

  • Supervisor: Gilles Bailly
  • Location: ISIR (Institut des Systèmes Intelligents et de Robotique), Campus Pierre et Marie Curie, 4 place Jussieu, 75005 Paris.

Contact person: 

  • Julien Gori
  • Tel : +33 1 44 27 51 21
  • Email : gori@isir.upmc.fr
  • Send your application by email, with [subject of the thesis] in the subject line, a CV and a  cover letter.
  • Application deadline: 15/05/2022

Download the thesis offer

Subject : Response generation models for solving multi-faceted information needs


The perspective of new information retrieval (IR) systems (e.g., search-oriented conversational systems or systems supporting complex search tasks) has fostered research on theoretical IR models either leveraging or supporting users’ interactions, for instance, through question clarification or interactive ranking models. However, very few works focus on the way of interacting with the user in natural language, which is critical for instance for conversational systems.

Project description:

The main objective of the thesis is to design question-answering models aiming at solving multi- faceted information needs. More particularly, given a document collection, our goal is to generate structured and complete answers, covering all facets of a complex information need.

To do so, approaches and models from information retrieval (IR) and natural language processing (NLP) will be necessary. Both research fields exploit Deep Learning (DL) techniques to model semantics underlying texts and generate new knowledge. More precisely, we showed in a premise work [DGS+22] the potential of data-to-text approaches [PDL19a, RSSG20, PDL19b] for complex answer generation. Our long-term objective is to fit with the conversational search setting and to deal with users’ interactions / conversational context [EPBG19, TY20] as well as include search task-oriented features in the generation process [FWZ+20, ZZW+20].

Two main lines of research stand out:

  • one is linked to the multiplicity of data sources (text, tables, figures, etc.) used to generate the output text and structure;
  • another one is more linked to the user satisfaction regarding the output in itself. The generated document should both be complete, understandable and explainable.

Application to industrial use cases will be envisioned in collaboration with the development team at Ecovadis.

Required Profile:

Master or engineering degree in Computer Science or Applied Mathematics related to machine learning/natural language processing/information retrieval. The candidate should have a strong scientific background with good technical skills in programming, and be fluent in reading and writing English.

Starting and duration (expected): October/November 2022, 36 months.


General information: 

  • Supervisor: Lynda Tamine (IRIT), Karen Pinel-Sauvagnat (IRIT), Laure Soulier (ISIR)
  • Collaboration as part of the thesis: CIFRE with Ecovadis
  • Start and duration (expected): October/November 2022, 36 months
  • Location: IRIT (Institut de Recherche en Informatique de Toulouse), Campus Paul Sabatier in Toulouse or ISIR (Institut des Systèmes Intelligents et de Robotique), Campus Pierre et Marie Curie, 4 place Jussieu, 75005 Paris.


Contact person : 

  • Laure Soulier
  • Tel : +33 1 44 27 74 91
  • Email : laure.soulier@isir.upmc.fr ; tamine@irit.fr ; sauvagnat@irit.fr ; skatrenko@ecovadis.com
  • Send your application by email, with [CIFRE Ecovidis] in the subject line, a CV, a cover letter, academic transcripts from L3 to M2, and letters of recommendation.
  • Application deadline: 31/08/2022 (applications processed on an ongoing basis, closing when we find a candidate)

Download the thesis offer

Job offers

Research engineer in robotics and computer science


In the context of the ANR-BMBF Learn2Grasp project on learning object grasping motions by a robot arm, ISIR AMAC team is looking for a research engineer to design and conduct experiments on real and simulated robotic systems.


The development and use of experimental systems for the study of robotic object manipulation in real and simulated environments, including implementing state of the art algorithms for perception, learning, decision and control, as well as integrating components developed by team members and ANR-BMBF Learn2Grasp project partners.

Required profile:

Engineer or PhD in robotics with solid computer science skills, or computer science or machine learning major with an experience in robotics.

Researched skills:

  • Software engineering and Python and C++ development
  • Machine learning (TensorFlow and/or PyTorch frameworks)
  • Robot arm control for manipulation
  • ROS framework
  • Visual perception (2D, 3D)
  • Robotic simulators (especially Bullet/pyBullet)
  • Running experiments and technical demonstrations on real robots – Literature review and state of the art search
  • Written and oral communication skills
  • Contributing to scientific articles and technical reports
  • Teamwork
  • Good grasp of English language (French is not required)

General Information: 

  • Position Type: Design Engineer
  • Contract start date: September 2022
  • Contract duration: 18 months
  • Level of education required: Engineering degree or PhD
  • Remuneration : Remuneration on the Research Engineer grid according to profile
  • Location: ISIR (Institut des Systèmes Intelligents et de Robotique), Campus Pierre et Marie Curie, 4 place Jussieu, 75005 Paris.

Contact person: 

  • Alex Coninx
  • alex.coninx(at)sorbonne-universite.fr
  • Send your application by email, with [name of the offer] in subject, a CV and a cover letter.
  • Deadline for application: 31/07/2022 (or later if no successful candidate)

Download this offer

Job: Instrument Development Expert

Job type: C1B43 – Instrument Development Expert

Category: A

Body: Research Engineer


Mission: The mission is to ensure the design and implementation of instrument projects according to scientific needs and/or to develop existing ones.

The position is open to the CNRS external competitive, for an assignment at ISIR. Opening of the campaign on June 07, 2022. 


Job Description:

  • Analyze scientific needs in robotics and translate them into technical specifications,
  • Propose concepts of intelligent instruments/devices,
  • Design intelligent instruments/devices, ensure their realization and guarantee their reliability,
  • Plan the development of intelligent instruments/devices,
  • Manage and control the integration of systems and sub-systems,
  • Provide expertise to the different robotic platforms of the laboratory,
  • Define and guarantee the maintenance strategy of the development tools and applications,
  • Carry out the test and validation procedures at the different stages of the projects,
  • Write technical documentations for the developed architectures,
  • Define the strategy for operational safety and fault tolerance of the systems,
  • Ensure compliance with health and safety rules,
  • Ensure a watch on the field in order to advise the researchers as well as possible,
  • To accompany the researchers in the capitalization of their experiments,
  • Train users of the laboratory’s equipment,
  • Participate in the life of the laboratory.

Skill descriptions:

  • Engineering technology and science, with strong knowledge in several of the following areas: computer science, electronics, mechanics, automation;
  • Programming languages (C/C++, Python),
  • Knowledge of ROS appreciated,
  • Knowledge of rapid prototyping (CAD) appreciated,
  • Environment and professional networks (general knowledge),
  • Project management methodology (general knowledge),
  • Written and oral presentation techniques,
  • English language: B1 to B2 (Common European Framework of Reference for Languages).

The missions of the research engineer are carried out in project mode within the technical department of the laboratory, which includes 6 people: 2 research engineers in computer science, 1 design engineer in computer science, 3 assistant engineers, 1 in computer science and 2 in mechanics.

The position is open to the CNRS external competition, for an assignment at ISIR. Opening of the campaign on June 07, 2022.


Postdoctoral or research engineer positions for the HCI Sorbonne group (Human Computer Interaction)


We have multiple postdoctoral and engineering positions in the HCI group (https://hci.isir.upmc.fr) at Sorbonne Université, Paris, France.


We are searching for curious minds who want to conduct cutting-edge research at the intersection of HCI with VR, Haptics, Robotics or AI. Possible topics/areas of research are:

  • Novel Interaction techniques in VR,
  • VR and haptics for gaming or training,
  • Computational models of decision-making and human performance,
  • AI-based recommendation systems,
  • Tele-operation and remote collaboration.

Some of our previous work in these areas:

Required profile:

For the postdoctoral position, a Phd degree in Computer science, HCI or other field related to our research areas is required.

Required skills:

  • strong programming and analytical skills,
  • strong background in at least one of the following areas (HCI, VR, Haptics, Robotics, AI).

More information : 

  • Type of position: Postdoctoral or Research Engineer position
  • Start date: as soon as possible
  • Duration: 1 to 2 years
  • Level of study required: Master 2 (for engineer), PhD (for post-doc)
  • Location: ISIR (Institut des Systèmes Intelligents et de Robotique), Campus Pierre et Marie Curie, 4 place Jussieu, 75005 Paris.


  • Gilles Bailly et Sinan Haliyo
  • Email : gilles.bailly(at)sorbonne-universite.fr ; sinan.haliyo(at)sorbonne-universite.fr
  • Application: Send your application by email, with a CV and a cover letter.
  • Application deadline: None

Download the offer

Internship offers

We don’t have any internship offers for the moment.