Location: Munich, Germany | Email: chayma.el.bahri.w@gmail.com
- 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.
| 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 |
- 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.
- 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.
- 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.
- English: Advanced (C1)
- German: Beginner (A1)
- French: Moderate (B2)
- Arabic: Native