Internship in Ai

Position description

**Category**:

- Mathematics, information, scientific, software

**Contract**:

- Internship

**Job title**:

- Internship in AI & LLM Adaptation of What-if Simulations for Business Processes H/F

**Subject**:

- AI & LLM Adaptation of What-if Simulations for Business Processes

**Contract duration (months)**:

- 6

**Job description**:
**Business Process Simulations (BPS)** are essential for analyzing, optimizing, and forecasting organizational workflows. **What-if simulations** enhance BPS by enabling analysts to test hypothetical changes—such as new tasks, altered decision points, or alternative flows—before implementation. A key challenge is to set correct simulation parameters for these changes, including task durations, distributions over decisions, and who would execute the involved tasks and when.

For example, a bank may introduce overnight delivery for newly issued credit cards, alongside the existing standard mail and express courier options. To simulate this scenario accurately, we must estimate how often customers will choose the new option and the duration of its associated tasks, like expedited printing, packaging, and courier handoff.

This project aims to develop adaptive methods that realistically model human behavior and decision-making for such what-if scenarios. For this purpose, we investigate the following approaches:

- **
AI techniques** similar to Retrieval-Augmented Generation (RAG) using low-dimensional text embeddings and clustering to identify historical process flows similar to new what-if scenarios. The scenario is encoded into a semantic vector, which is then compared to past cases using similarity metrics like cosine distance. Once similar instances are retrieved, their task durations and decision probabilities are extracted and used to estimate the unknown parameters in the new scenario
- **
Large Language Models (LLMs)** are able to predict human decisions and responses. Our goal is to use foundation models such as Mistral to directly predict task durations or decision distributions for what-if scenarios. The approach involves optimizing prompt strategies and fine-tuning the models to ensure context-aware, plausible outputs that are aligned with historical and expert knowledge.

Your task:

- Perform a literature review about the current state-of-the-art in what-if simulations for BPS and their adaptation
- Develop together with your supervisor ideas for new adaptation mechanisms that are based on historical data and/or LLM suggestions on how humans might behave
- Evaluate your methods by comparing them to baselines and performing ablation studies
- Write a scientific report about your findings, preferably as a scientific workshop or conference contribution

The internship will be carried out at CEA Grenoble.

**Methods / Means**:

- Python, LLM, Machine Learning

**Applicant Profile**:

- #1: Motivation for scientific work and the development of AI tools
- Proficient in Python and development tools (git, debugging,...)
- Master student in Computer Science or a similar field or related expertise
- Good English level in speaking and writing
- Nice to have: Familiarity with Machine Learning and the usage of LLMs via API

Position location

**Site**:

- Grenoble

**Job location**:

- France, Auvergne-Rhône-Alpes, Isère (38)

**Location**:

- Grenoble

**Languages**:

- English (Fluent)
- French (Intermediate)

**Prepared diploma**:

- Bac+4/5 - Diplôme de recherche technologique (DRT/DRI)

**Recommended training**:

- Master Degree in Computer Science / Applied Mathematics

**PhD opportunity**:

- Oui

Requester

**Position start date**:

- 05/01/2026

General information

**Organisation**:
The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas:

- defence and security,
- nuclear energy (fission and fusion),
- technological research for industry,
- fundamental research in the physical sciences and life sciences.

Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners.

The CEA is established in ten centers spread throughout France

**Reference**:2025-37790

**Description de l'unité**:

- Direction de la Recherche Technologique (DRT)

CEA's DRT harnesses scientific expertise to drive innovation that strengthens the competitiveness of French companies. By developing, securing, and transferring advanced technologies, DRT supports industries ranging from traditional sectors to cutting-edge high-tech fields, serving businesses of all sizes. Its innovation initiatives are deployed across all regions of France, helping local enterprises enhance their performance and stand out in the market. Through this approach, CEA fosters long-term job creation and economic value, closely aligned with industrial needs