Skip to content
View amijen's full-sized avatar

Block or report amijen

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
amijen/README.md

Welcome to Amine Sellami's GitHub! ๐Ÿš€

๐Ÿค– AI Engineer Intern @Renault Group

๐ŸŽ“ Graduated with Excellent Honors from ร‰cole Polytechnique de Tunisie

๐Ÿ“˜ Master 2 TIDE (Big Data & Data Science in Enterprise) student at Panthรฉon-Sorbonne

๐Ÿ“ Paris, France

๐Ÿ“ซ Email: aminesellami0110@gmail.com

๐Ÿ’ผ LinkedIn: www.linkedin.com/in/amine-sellami61


๐Ÿ’ก My Interests

I am an AI Engineer passionate about building GenAI pipelines, LLM/RAG applications, and end-to-end ML systems in production. My current focus areas:

  • ๐Ÿง  LLMs & Agentic Systems โ€” structured prompting, RAG, multi-agent orchestration, guardrails
  • ๐Ÿ‘๏ธ Computer Vision โ€” multimodal pipelines, fine-tuning vision foundation models (CLIP)
  • ๐ŸŽฏ Reinforcement Learning โ€” exploring RLHF & policy optimization
  • โš™๏ธ MLOps & Cloud โ€” GCP (Vertex AI, BigQuery), reproducible pipelines, monitoring & traceability

I enjoy transforming AI research into high-value business solutions and collaborating with cross-functional teams.


๐Ÿ›  Skills & Tools

๐Ÿ‘ฉโ€๐Ÿ’ป Programming

Python R SQL SAS LaTeX

๐Ÿค– GenAI, LLMs & Agents

Transformers LLaMA GPT Gemini LangChain CrewAI RAG Agentic AI MCP Groq Ollama Fine-Tuning Prompt Engineering

๐Ÿ”ฌ Machine Learning & Deep Learning

PyTorch TensorFlow Keras Hugging Face Scikit-learn LightGBM XGBoost CLIP

๐Ÿ“ˆ Time Series, Forecasting & Clustering

Time Series K-Means Monte Carlo

๐ŸŽฏ Optimization

Gurobi PuLP

๐ŸŽฒ Stochastic & Financial Modeling

Nelsonโ€“Siegel Vasicek CIR Stochastic Programming Robust Optimization

โšก Big Data

Apache Spark PySpark

โ˜๏ธ Cloud & MLOps

GCP Vertex AI BigQuery Docker

๐Ÿ—„๏ธ Databases, Vector DBs & Backend

PostgreSQL pgvector Pinecone FastAPI

๐Ÿ“Š Data & Visualization

Pandas NumPy Seaborn Matplotlib Plotly Streamlit

๐Ÿ•ธ๏ธ Web Scraping & Data Extraction

Selenium Playwright BeautifulSoup

๐Ÿ›  Dev Tools & Collaboration

VS Code Git GitLab GitHub Agile


๐ŸŒ Languages

Arabic โ€” Mother tongue | French โ€” Fluent | English โ€” Fluent (TOEIC 880/990)


Curious, adaptable, and driven by continuous learning โ€” always exploring new AI technologies. ๐Ÿš€

Pinned Loading

  1. Multi-Agent-Research Multi-Agent-Research Public

    ๐Ÿš€ End-to-end Generative AI pipeline using autonomous agents, LLM orchestration, web search, scraping, and iterative report refinement with LangChain.

    Python

  2. Amine_Coffee_Shop Amine_Coffee_Shop Public

    ๐Ÿง  Multi-agent conversational AI system (chatbot) using LLMs, Retrieval-Augmented Generation (RAG), vector databases, and recommendation algorithms to deliver contextual customer support and personaโ€ฆ

    Jupyter Notebook 2

  3. Deep-Past-Challenge-Translate-Akkadian-to-English-Kaggle Deep-Past-Challenge-Translate-Akkadian-to-English-Kaggle Public

    ๐Ÿค– NLP pipeline for low-resource machine translation using ByT5, advanced text normalization, custom training loops, and optimized Transformer inference.

    Python 1

  4. Athlete-Performance-and-Injury-Prediction Athlete-Performance-and-Injury-Prediction Public

    ๐Ÿƒโ€โ™‚๏ธ Multimodal AI pipeline for athlete performance and injury risk prediction, combining wearable sensors, health data, and food image analysis. Includes feature engineering, CalorieCLIP-based nutโ€ฆ

    Jupyter Notebook

  5. AirQo-Low-Cost-Air-Quality-Monitor-Calibration-Challenge AirQo-Low-Cost-Air-Quality-Monitor-Calibration-Challenge Public

    ๐Ÿ“Š End-to-end environmental ML solution for air quality forecasting across African cities. Includes large-scale data preprocessing, geospatial encoding, temporal feature engineering, and neural netwโ€ฆ

    Jupyter Notebook

  6. AI_Tennis_Assistant AI_Tennis_Assistant Public

    ๐Ÿค– Agentic RAG assistant built with LangGraph, LangChain, FastAPI, and pgvector that answers ITF & Grand Slam tennis-rule questions with self-correction, multi-turn memory, and source-grounded page โ€ฆ

    Python