Improving the Effectiveness of LLM-Assisted ISS Generation from Design Specification H/F

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

2024-33881  

Description de l'unité

The French Atomic Energy and Alternative Energies Commission (CEA) is a major player in research, development and innovation. This technological research organization is active in three main areas: energy, information and health technologies, and defense. Recognized as an expert in its fields, CEA is fully integrated into the European research area and is expanding its presence internationally. The Laboratory for Systems and Technology Integration (LIST), located in the southern Île-de-France region (Saclay), has the mission of contributing to technology transfer and promoting innovation in the field of parallel computing systems.

The Environmental Design and Architecture Laboratory (LECA), within the Digital Systems and Integrated Circuits Department (DSCIN), is a multidisciplinary technological research team comprising experts in hardware IP design and simulation tools.

Position description

Category

Mathematics, information, scientific, software

Contract

Internship

Job title

Improving the Effectiveness of LLM-Assisted ISS Generation from Design Specification H/F

Subject

The internship aims to enhance the performance of large language models (LLMs) in generating Instruction Set Simulator (ISS) code by using Reinforcement Learning (RL) to optimize and automate prompt tuning. Additionally, the internship seeks to expand dataset coverage by using simulators such as QEMU (Quick Emulator) in-the-loop to simulate and evaluate a wider range of architectures, enabling access to diverse implementations and increasing dataset diversity. While RL will be the primary focus, alternative methods can also be explored throughout the internship.

Contract duration (months)

6

Job description

The main activities will involve using RL to dynamically adjust the prompts fed to the LLM, guiding it to improve code correctness, compilation success, and functional efficiency. Open questions for investigation include, but are not limited to, how to define rewards that balance compilability and functionality, how feedback from these rewards can be used to refine future prompts, and what strategies can effectively integrate RL rewards into the prompt generation process. The RL agent will iteratively adjust the prompt based on feedback from compilation and functional tests, using QEMU to assess the quality of the generated code. By simulating multiple architectures in the QEMU environment, the internship will aim to broaden the dataset coverage, making the model more adaptable to different hardware implementations. The results of this work have the potential to contribute significant insights into this field and may lead to publication in relevant conferences.

During this internship, the student will gain practical experience with advanced AI techniques, such as RL and automatic prompt tuning, while enhancing their knowledge of LLM-based code generation. This project provides a valuable opportunity to develop key skills in AI-driven hardware design and to contribute to innovative research.

Methods / Means

Python, C/C++

Applicant Profile

Level required: Master's degree

Duration: 6 months

Skills: Understanding of AI, especially LLM and RL, and knowledge of HW architecture design would be a plus.

Python, C/C++

English, teamwork, curiosity

 

In line with CEA's commitment to integrating people with disabilities, this job is open to all.

 

Position location

Site

Saclay

Job location

France, Ile-de-France, Essonne (91)

Location

  Palaiseau

Candidate criteria

Languages

English (Fluent)

Prepared diploma

Bac+5 - Master of Science

PhD opportunity

Non

Requester

Position start date

03/03/2025