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
2026-42033
Description de l'unité
This internship is part of a joint project between CEA-Leti and CEA-List to enable energy efficient deployment of generative AI models at the edge with novel memory technologies. The project brings together a forefront ecosystem for AI model development (CEA-List) and electronic technologies development (CEA-Leti).
The intenship is hosted at the "Laboratoire des Dispositifs pour les Mémoires et le Calcul (LDMC)" from CEA Leti. The LDMC laboratory explores and develops innovative Non-Volatile Memory devices (resistive NVM notably) and novel computing solutions (neuromorphic solutions, in-memory computing, etc.). Our laboratory brings together expertise in nanoelectronic devices and technology, as well as circuit design for computing and embedded memory.
Position description
Category
Micro and nano technologies
Contract
Internship
Job title
Scaling analog in-memory computing towards large generative AI models H/F
Subject
Your work will span device-to-algorithm co-design, focusing on state-of-the-art small language model engineering and compression and its co-optimization with memory technology characteristics and constraints. You will work within CEA-Leti and CEA-List institutes, benefiting from a forefront ecosystem for AI model development and electronic technologies development.
Contract duration (months)
6
Job description
The recent evolution of generative AI models has been driven by an exponential increase on their number of computing parameters, increasing the memory resources required for their acceleration as well as exacerbating the criticality of data movement within the system on both energy efficiency and computing latency. Analog in-memory computing (aIMC) offers a promising approach to reduce data movement and therefore enhances energy efficient computing capabilities at the edge. Nevertheless, memory technology non-idealites make aIMC scalability to large scale generative AI models with high performance challenging.
Your work will span device-to-algorithm co-design, focusing on state-of-the-art small language model engineering and compression and its co-optimization with memory technology characteristics and constraints. You will work within CEA-Leti and CEA-List institutes, benefiting from a forefront ecosystem for AI model development and electronic technologies development.
Why join our team? We propose:
- A cutting-edge, innovative experience with strong potential for industrial development
- Training courses to strengthen your skills or acquire new ones
- A work environment in the heart of the Grenoble metropolitan area, easily accessible via the soft mobility options promoted by the CEA
- A recognized work-life balance environment
- A diversity and inclusion policy
- Corporate catering
Applicant Profile
With a background in computer science and AI or electronics, you are a problem solver with strong adaptability and communication skills. You are curious and you appreciate team work. You have a keen interest in both generative AI models applied to next-generation computing systems and novel electronic devices.
Position location
Site
Grenoble
Job location
France, Auvergne-Rhône-Alpes, Isère (38)
Location
Grenoble
Candidate criteria
PhD opportunity
Oui
Requester
Position start date
08/02/2027
Create candidate area
