My current research focuses on applying Artificial Intelligence and Machine Learning to FPGA benchmarking, Electronic Design Automation, and embedded systems.

Current Research Internship

FPGA Benchmarking Framework for AI-Based EDA Tools

Institute: Institut d’Électronique et des Technologies du numéRique (IETR)
Location: Nantes, France
Duration: February 2026 – July 2026
Role: Research Intern

  • Built an AI/ML-based FPGA benchmarking framework using XGBoost.
  • Created ML-ready Vivado datasets from congestion, routing, utilization, unrouted nets, and runtime metrics.
  • Developed an AI-assisted adversarial netlist generation flow for benchmarking AI-based EDA tools.
  • Designed a Python and NetworkX graph generator for FPGA-aware circuit generation.
  • Automated Verilog and XDC generation for AI-driven FPGA routing-stress testing.

Research Interests

  • Artificial Intelligence for Electronic Design Automation
  • Machine Learning for FPGA routing congestion prediction
  • AI-assisted adversarial circuit and netlist generation
  • FPGA implementation analysis using Vivado golden-reference results
  • Embedded AI and Edge AI for low-power intelligent systems
  • Hardware/software co-design for connected and embedded objects

Research Skills

  • Machine Learning: XGBoost, CNN classification, dataset preparation, model training, prediction, and evaluation
  • Deep Learning: Convolutional Neural Networks, medical image classification, model accuracy evaluation, and diagnostic report generation
  • FPGA Design: Vivado, Verilog, XDC constraints, routing congestion analysis, implementation metrics
  • Graph-Based Generation: Python, NetworkX, DAG-based circuit generation, FPGA-aware constraints
  • Embedded Systems: Arduino, C/C++, embedded software, Bluetooth communication, edge computing, and low-power system design
  • Signal Processing: Advanced signal processing, antenna processing, AI for digital communications
  • Software Development: Python, PHP, SQL, JavaScript, HTML, CSS, Bootstrap, and web-based application development

Academic Background Supporting Research

I am pursuing a Master's in Embedded Technologies and Artificial Intelligence at Nantes Université, with coursework in AI fundamentals, AI for advanced digital communication, embedded systems architecture, embedded OS, edge computing, hardware/software architecture design, advanced signal processing, antenna processing, power consumption and reliability, embedded software, and connected objects.

Research Goal

My goal is to develop intelligent FPGA benchmarking methods that use AI and machine learning to generate challenging circuit scenarios, evaluate AI-based EDA tools, and support more reliable FPGA and VLSI design workflows.