Post doctoral in Computer Science

Télécom SudParis; Palaiseau; Sur place; EUR 35 000 - 45 000; Plein temps

Résumé du poste

A leading research institution in Palaiseau is seeking a postdoctoral researcher to contribute to an innovative project on developing a generative recommendation system for digital environment assessments. The role involves collaboration with industry partners, applied research, and access to essential resources for successful project execution.

Prestations

Teleworking possible

Restaurant and cafeteria on site

Accessibility by public transport

Staff association and sports association on campus

Qualifications

• PhD or Doctorat for less than 3 years of experience.
• Strong knowledge of LLMs and generative models.

Responsabilités

• Design and develop an advanced recommendation system.
• Conduct needs and standards analysis for questionnaires.
• Validate through real-world use cases with Board Of Cyber.

Connaissances

Large Language Models

Python

Java

C

C++

Formation

PhD

Outils

AWS

Azure

GCP

Description du poste

Organisation/Company Télécom SudParis Department TELECOM SUDPARIS Research Field Computer science Researcher Profile Recognised Researcher (R2) Positions Postdoc Positions Country France Application Deadline 12 Jun 2025 - 00:00 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 40 Offer Starting Date 1 Jul 2025 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

MISSIONS:

As part of the collaborative EVA 2026 project with the French startup Board Of Cyber, this postdoctoral position will contribute to the design, development, and evaluation of an advanced recommendation system for the generation of digital environment assessment questionnaires. The project aims to address the increasing complexity of assessing digital environments by leveraging generative models and large language models (LLMs) to automate and personalize the generation of audit and compliance questionnaires aligned with major standards (e.g., ISO, NIST). These questionnaires are structured sets of questions used to assess the security posture of IT systems and their compliance with established organizational standards.

Expected outcomes of the project include:

• The construction of a contextual meta-questionnaire, structured using semantic representations and ontologies, capable of capturing and organizing heterogeneous questionnaires;
• The development of a generative recommendation system capable of suggesting, generating, and pre-filling relevant questionnaires based on user profiles, historical assessments, and contextual information.

The postdoctoral researcher will work within an academic team (SAMOVAR/ACMES group), in close collaboration with engineers from Board Of Cyber. The position involves applied research, experimentation with LLM-based architectures, the development of prototypes, and validation through real-world use cases provided by the industrial partner. The candidate will have access to the necessary computing resources and datasets required for the research activities.

ACTIVITIES:

1/ Needs and Standards Analysis

• Study key standards (ISO, NIST, etc.) and various questionnaires provided by Board of Cyber to extract the structural elements of questionnaires
• Analyze real responses to these questionnaires provided by Board of Cyber
• Identify contextual criteria influencing the generation of questionnaires (e.g., type of organization, sector of activity, etc.)

2/ Design of the Meta-Questionnaire based on the findings from the needs analysis

3/ Development of a Generative Recommendation System

• Select and adapt existing language models (LLMs) and generative models
• Train and evaluate these models on provided or simulated datasets
• Implement recommendation, generation, and pre-filling mechanisms for questionnaires tailored to user profiles

4/ Validation through Real-World Use Cases in collaboration with Board Of Cyber

Level of training and / or experience required:

• PhD or Doctorat for less than 3 years

Essential skills, knowledge and experience:

• Strong knowledge of large language models (LLMs) and generative models (e.g., GPT, T5, BERT, etc.).
• Proficiency in Python, Java, C, or C++.

Advantageous skills, knowledge and experience:

• Experience with recommendation systems.
• Familiarity with cloud platforms and tools (e.g., AWS, Azure, GCP).
• Prior experience in the field of IT audit, compliance, or system evaluation.

Abilities and skills:

• Strong motivation for applied and interdisciplinary research.
• Ability to work effectively in collaborative academic/industrial environments.
• Creativity and problem-solving skills.
• Autonomy and strong organizational skills.

Specific Requirements

• Nature of the contract: CDD / 12 months
• To apply, please send us a CV, a cover letter
• Location of the position : Palaiseau (France)
  The positions offered for recruitment are open to all with, on request, accommodations for candidates with disabilities

Working conditions: Teleworking possible, restaurant and cafeteria on site, accessibility by public transport (with employer's participation) or close to main roads, staff association and sports association on campus