> Markdown version of [/jobs/ext/4051014-internship-combining-analytical-and-ml-models-for-efficient-hw-performance-prediction-saclay-h-f](https://www.wearedevelopers.com/jobs/ext/4051014-internship-combining-analytical-and-ml-models-for-efficient-hw-performance-prediction-saclay-h-f). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Internship: Combining Analytical and ML Models for Efficient HW Performance Prediction - Saclay H/F

- **Company:** CEA Industrie
- **Location:** Saclay, France
- **Experience:** Internship
- **Contract:** Internship / Graduate position
- **Skills:** Artificial Intelligence, C++ (Programming Language), Python (Programming Language), Machine Learning, System on a Chip, Git
- **Published:** October 16, 2026
- **Apply:** https://www.emploi.cea.fr/offre-de-emploi/emploi-internship-combining-analytical-and-ml-models-for-efficient-hw-performance-prediction-saclay-h-f_42085.aspx

## About the Role

Within the CEA List, the Electronics Design Automation and Architectures Laboratory (LECA) has the mission to design innovative and flexible system-on-chip architectures that meet the challenges of performance, cost, energy consumption, safety and security, targeting critical embedded systems and HW accelerators for embedded AI. To reduce the development time and improve the quality of these architectures, the team of experts develop innovative design tools and methods., * Required level: Master's degree or Engineering diploma

 * Required Skills: Familiarity with AI, knowledge of computer architecture, proficiency in Python and C/C++, and experience with Git
 * Other Qualities: Collaborative mindset and a genuine curiosity

## Description

Using the CVA6, CVA6S, CVA6S+ architectural evolution as a case study, the internship will explore:

 * Hybrid modeling: Combining simulation ML-driven performance insights with analytical architectural models.
 * Transferability: Evaluating whether models developed for one hardware generation can be adapted to subsequent generations with limited retraining or recalibration.
 * Design-space exploration: Assessing the ability of hybrid models to efficiently predict the impact of architectural modifications.

The internship aims to develop and evaluate a hybrid modeling methodology that balances accuracy, expressiveness, and transferability across hardware generations. The ultimate objective is to assess its potential for enabling flexible hardware design-space exploration, reducing reliance on costly cycle-accurate simulations.

References

[ISCA'25] Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion

[ICCAD'23] PANDA: Architecture-Level Power Evaluation by Unifying Analytical and Machine Learning Solutions