Skip to content
View GuechtouliAnis's full-sized avatar
16 followers · 31 following

Highlights

  • Pro

Block or report GuechtouliAnis

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
GuechtouliAnis/README.md

👋 Hello there, I'm Anis

AI Engineer 🤖 | Data Scientist 📊 | Football Enthusiast ⚽

Where data sparks the light of revelation. ✨

📜 About Me

I'm an AI Engineer building production-ready LLM and ML systems to automate workflows, enhance decision-making, and deliver actionable insights. I specialize in RAG architectures, AI assistant development, and end-to-end deployment pipelines.

Currently working at Groupe HYDRAPHARM as an AI Engineer, where I develop AI and LLM systems, work on RAG-based assistants and interactive applications, and collaborate with teams to implement AI solutions.

Previously, I worked at SIG Service as a Business Analyst, supporting large-scale Odoo migration projects (Odoo 8 to Odoo 13) using Apache NiFi. I debugged and maintained high-volume NiFi flows and authored comprehensive technical documentation covering the entire data migration pipeline.

Before that, I completed a 7-month Data Scientist role at Djezzy, where I built an NLP-powered HR chatbot using Large Language Models, structured and cleaned Q&A data for model training, and applied prompt engineering to improve answer quality.

My journey started with a 6-month internship at CAAR as a Data Analyst, where I created dashboards to monitor automotive insurance metrics and delivered insights to support strategic decisions.

I hold a Master's degree in Data Science from Université d'Alger 1, with expertise spanning applied AI, machine learning, natural language processing, and data analytics. I'm passionate about solving complex problems and transforming data into real-world impact.

📧 Contact Me

For more information, collaborations, or if you'd like to connect on AI, data science, or football analytics, feel free to reach out!

Email

LinkedIn

Kaggle

Resume

I look forward to connecting with you!

⭐ Tech Stack

Throughout my career in AI and data science, I've developed expertise in various skills and tools. I've used these in production environments and projects, from initial data analysis to building and deploying AI-powered applications.
Here's an overview of what I work with:

Programming & Data Science

Python

SQL

Pandas

PySpark

Scikit-learn

Matplotlib

Plotly

Streamlit

AI & NLP Tools

LangChain

Ollama

Hugging Face

Unsloth

Data Management & ETL

SQLite

PostgreSQL

Apache NiFi

Neo4j

Dashboarding & BI Tools

Tableau

Power BI

Excel

Development & Version Control

Jupyter

Kaggle

Git

Docker

Pinned Loading

  1. xG-model xG-model Public

    An Expected Goals (xG) model built with StatsBomb open data. The project covers data scraping, cleaning, feature engineering, model training, and evaluation to estimate goal probabilities from shot…

    Jupyter Notebook 2

  2. Telco-churn-prediction Telco-churn-prediction Public

    Streamlit web app for Telecom Customer Churn Prediction using machine learning. Includes multiple optimized models (XGBoost, Random Forest, etc.), dynamic UI, real-time probability scoring, and an …

    Jupyter Notebook

  3. Machine-Learning-College-Projects Machine-Learning-College-Projects Public

    This repository contains four machine learning projects developed during college, covering email spam detection, emotion classification in Urdu, voice classification, and iris recognition. Each pro…

    Jupyter Notebook

  4. Football-Data-Scraping Football-Data-Scraping Public

    A Jupyter Notebook project to scrape detailed football data from FBref, covering various leagues. The repository includes both the data collection process and a final cleaned dataset for immediate …

    Jupyter Notebook 5

  5. TSF TSF Public

    A collection of projects completed during The Sparks Foundation internship, including a retail analytics dashboard and two small machine learning models.

    Jupyter Notebook

  6. Knapsack Knapsack Public

    A web application built with Streamlit to solve the knapsack problem using mixed-integer optimization. Users can input the values and weights of different items, set a knapsack limit, and select be…

    Python