Open to a PFE internship · 2027

Soulaima Sellemi

AI Engineer — LLM Agents & Deep Learning

I turn promising AI research into tools people can actually trust: multi-agent LLM pipelines, RAG systems and deep-learning models, evaluated on real-world data — not just benchmarks.

Download CV (opens in a new tab) Get in touch
(opens in a new tab) (opens in a new tab)
2R&D internships
at Larodec Lab
937KGerrit changes
mined & analysed
+7.4 ptsaccuracy over a
published ICSE '26 baseline
97.0%Dice score on
PH2 segmentation

About me

I'm a final-year software engineering student at the National School of Computer Science (ENSI), University of Manouba, after two years of Mathematics & Physics preparatory classes at IPEIB.

What drives me is the gap between a promising paper and a tool someone can rely on. In my research internships I take published methods, test them on messy, real-world data, find out where they break, and build something better.

I'm comfortable across the whole path — from training and evaluating models to shipping them with LangChain / LangGraph, Docker and Jenkins CI/CD.

Currently looking for an end-of-studies (PFE) internship in AI / LLM engineering.

  • location Manouba, Tunisia
  • degree Engineering, Software Eng. (2024–2027)
  • languages Arabic (native) · French (C1) · English (B2)
  • also Treasurer, ENSI Robotics Association

Research experience

Summer 2026Larodec Laboratory, ENSI

AI R&D Intern

Toward AI-Assisted Decomposition of Large Pull Requests into Reviewable Changes

Large pull requests are hard to review. I tested whether a published multi-agent LLM framework could split them into smaller, reviewable changes — on real developer history instead of synthetic benchmarks.

65.0%Atomizer (ICSE 2026) on real Gerrit data
72.4%my taxonomy-routed pipeline
κ = 0.896inter-rater agreement on taxonomy
  • Mined 937,327 Gerrit changes from 7 ecosystems into 142 validated change-split cases, each traced to the developer's own words.
  • Built a taxonomy of why and how developers split changes (κ = 0.896 and 0.769).
  • Diagnosed over-splitting as the main cost driver, then designed a taxonomy-routed pipeline that beat the baseline.
Multi-agent LLMsLangGraphMining software repositoriesEmpirical evaluation
Summer 2025Larodec Laboratory, ENSI

Deep Learning Intern

AC-MambaSeg: Hybrid CNN-Mamba Model for Skin Lesion Segmentation

Reproduced and extended a hybrid architecture combining CNNs with Mamba state-space blocks, CBAM and attention gates for medical image segmentation, in PyTorch Lightning.

97.0%Dice on PH2 (CNN baseline 95.0%)
94.2%IoU on PH2 (baseline 91.0%)
90.5%Dice on ISIC 2018, ahead of SM-UNet
  • Hair-removal preprocessing, AdamW and fine-tuning raised ISIC 2018 Dice from 85.3% to 90.5%.
PyTorch LightningMamba / SSMMedical imagingOpenCV

Projects

Click a project to see how it works, the results and the tech behind it.

Skills

LLMs & Agents

LangChainLangGraphMulti-agent pipelinesRAGHybrid search (BM25 + embeddings)LLM-as-a-judgeLlama 3GroqOllama

Deep Learning & NLP

PyTorchPyTorch LightningTensorFlowTransformersONNX RuntimespaCyGLiNEROpenCV

Programming & Web

PythonJavaC / C++SQLStreamlitMySQLAngularMongoDB

DevOps & Tools

GitDockerLinuxJenkinsSonarQubeMavenCI/CDTree-sitterPyDrillerLaTeX

Certifications

  • NVIDIA — Fundamentals of Deep Learning · 2026
  • NVIDIA — Computer Vision for Industry · 2026
  • Talan — Building GenAI-based Chatbots · 2025
  • Microsoft — AI Conduit VS Code · 2025
  • DeepLearning.AI — Advanced Learning Algorithms · Coursera

Activities

  • Treasurer, Executive Board — ENSI Robotics Association · 2025–2026
  • Member — IEEE ENSI Student Branch · 2024–2025
  • Member — ENSI Junior Enterprise · 2024–2025
  • Member — ENSI Competitive Programming Club · 2024–2025

Contact

Let's build something trustworthy.

I'm looking for a PFE internship in AI / LLM engineering. If your team works on agents, RAG or applied deep learning, I'd love to talk.