Skip to content
View chaymabh's full-sized avatar

Block or report chaymabh

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 don’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 user’s behavior. Learn more about reporting abuse.

Report abuse
chaymabh/README.md

Data Scientist | LLMs, Graph AI & Agentic Systems

Location: Munich, Germany | Email: chayma.el.bahri.w@gmail.com

LinkedIn Email


Core Competencies

  • Agentic AI & LLM Engineering: Architecting multi-agent production pipelines using LangGraph and LangChain for complex task orchestration. Serving fine-tuned open-source language models via vLLM, Ollama, and Hugging Face Transformers.
  • Graph Machine Learning: Designing Graph Neural Network architectures (GraphSAGE, GAT, GCN) for anomaly detection and structural graph pattern analysis using PyTorch Geometric (PyG) and DGL.
  • Data & Search Systems: Structuring multi-modal data strategies across graph stores (Neo4j), search engines (Elasticsearch), and relational systems (PostgreSQL).
  • MLOps & Backend Infrastructure: Building low-latency RESTful APIs with FastAPI and Flask, and deploying end-to-end ML services on AWS and OVH cloud infrastructure.

Technical Stack

Domain Technologies
Agentic AI & LLMs LangGraph, LangChain, LlamaIndex, vLLM, Ollama, Hugging Face
Graph AI & Analytics PyTorch Geometric (PyG), Deep Graph Library (DGL), NetworkX, Neo4j
Core ML & Vision PyTorch, TensorFlow, Scikit-Learn, XGBoost, OpenCV, YOLO
Data & Databases PostgreSQL, Elasticsearch, MongoDB
Backend & Cloud FastAPI, Flask, AWS, OVH, Git, Linux
Languages Python, C++, Java, MATLAB

Technical Accomplishments & Applied Experience

Autonomous Multi-Agent Workflows

  • Developed multi-agent orchestration pipelines using LangGraph to process complex, multi-step business logic.
  • Automated data validation routines and error handling across heterogeneous data sources.

Graph Neural Networks & Anomaly Detection

  • Conducted specialized research on GNN architectures for robust structural anomaly detection.
  • Engineered feature extraction pipelines and graph embeddings to enhance classification performance on complex topologies.

Production Model Serving

  • Deployed microservices for real-time inference using FastAPI and Flask on cloud infrastructure.
  • Implemented path optimization algorithms ($A^*$ and Dijkstra) and vision tracking modules for automated systems.

Languages

  • English: Advanced (C1)
  • German: Beginner (A1)
  • French: Moderate (B2)
  • Arabic: Native

Pinned Loading

  1. Getting_Started_with_Graph_Neural_Networks_GNNs_Using_PyTorch_Geometric Getting_Started_with_Graph_Neural_Networks_GNNs_Using_PyTorch_Geometric Public

    This repository is designed to introduce beginners to GNNs and provide a series of tutorials on various techniques in Geometric Machine Learning. Whether you're a student, developer, or researcher,…

    Jupyter Notebook 2 1

  2. TextMining-ScrapCleanSummarize TextMining-ScrapCleanSummarize Public

    This repository contains code for scraping, cleaning, and summarizing text data from websites. It provides a comprehensive process for extracting valuable information from online sources and conden…

    Python 2 1

  3. Anomaly_detection_with_AdaGNN Anomaly_detection_with_AdaGNN Public

    Jupyter Notebook 1

  4. Data_Insights_From_Images Data_Insights_From_Images Public

    The Instagram Image Analysis Tool is a Python application designed for data scientists and enthusiasts who want to scrape and analyze images from Instagram.

    Python 1

  5. Marathon-Support-Agent Marathon-Support-Agent Public

    Python 1