Skip to content
View jean-cheramy's full-sized avatar

Block or report jean-cheramy

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
jean-cheramy/README.md

👋 Hi, I'm Jean

I'm a Data Science and AI coach at BeCode, with hands-on experience as an NLP engineer and a deep curiosity for everything in the data domain, from classical statistics to cutting-edge LLMs.

💼 What I Do

As a coach, I guide job seekers through the intricacies of data science (ML and AI as well), analysis and engineering, while continuing to build and explore solutions myself. I’m also passionate about cloud-native development, CI/CD, and DevOps practices. I find it deeply satisfying to design robust, elegant workflows that make data solutions reproducible, scalable, and easy to deploy, turning prototypes into production-ready systems.

My background includes working on:

  • 🔎 Semantic search engines leveraging dense vector representations and similarity measures
  • Keywords generation and deduplication
  • ☁️ Cloud-native Python applications for scalability
  • ⚙️ APIs, and deployment workflows

🧰 Tech Stack

🔧 Data Engineering

Python Scraping Docker FastAPI SQL AWS Azure Linux DevOps Git Apache Airflow Apache Spark Prefect

📊 Data Analysis

Pandas NumPy SQL Tableau Power BI Jupyter

🤖 Data Science & ML

Hugging Face scikit-learn spaCy NLP LLM RAG ML & DL TensorFlow PyTorch LangChain

🎓 Coaching Philosophy

I believe learning by doing is the most effective path. My goal as a coach is to bridge the gap between theory and practice, encouraging students to build real-world solutions, write clean code, and understand the "why" behind the tools.

🧠 Always Learning

I'm currently diving deeper into:

  • Retrieval-augmented generation (RAG)
  • MLOps best practices
  • Agents

📫 Let’s Connect

Pinned Loading

  1. illegal_deforestation_detector illegal_deforestation_detector Public

    Resource-efficient AI project for detecting illegal deforestation from audio data. Trains and compares multiple models—Linear Regression, Random Forest, SVM, and CNN—on 3-second chainsaw recordings…

    HTML

  2. rtbf-news-topics-modeling rtbf-news-topics-modeling Public

    RTBF news scraper and topic modeling with Python: scrape RTBF en-continu articles using Selenium/BeautifulSoup, then uncover latent topics via BERTopic and export results for Tableau analysis.

    Python

  3. VoteWise VoteWise Public

    VoteWise is a prototype system that helps users explore and summarize political party positions in Belgium. It leverages retrieval-augmented generation (RAG).

    Python

  4. keytrade-trustpilot-analysis keytrade-trustpilot-analysis Public

    End-to-end data science project analyzing 1,000+ multilingual Trustpilot reviews of Keytrade Bank. Includes web scraping, EDA, sentiment analysis with classical and modern NLP models, and generativ…

    HTML

  5. attendance-bot-discord attendance-bot-discord Public

    Discord bot that tracks learner attendance in voice channels, sends daily reports on weekdays, and runs as an Azure Container App.

    Python