Naji Najari, Ph.D.

- Built multiple production agents within a multi-agent AI platform used by end-users and internal teams: documentation Q&A (RAG), CRM contact management, campaign analytics and recommendation, and more | LangChain, LangGraph, Google ADK, LangFuse - Exposed Brevo's public APIs as MCP servers, enabling developers to use Brevo tools directly from AI coding assistants (Claude, Cursor) | FastMCP, FastAPI - Implemented production-grade RAG pipelines for real-time customer query answering from Brevo's knowledge base | Ragflow, LangChain - Integrated Langfuse for end-to-end LLM tracing and monitoring; built automated quality checks using LLM-as-a-judge with human-in-the-loop annotation workflows - Fine-tuned BERT for multilingual spam and fraud detection across email traffic | HuggingFace Transformers, CI/CD - Trained and deployed ML audience recommendation models to optimize e-commerce campaign targeting | ZenML, MLOps, MLFlow - Built scalable API endpoints serving AI microservices: image generation for email campaigns, speech recognition for phone calls | FastAPI, Kubernetes

- Led a cross-functional team of 6-8 (data scientists, software engineers, front-end developers) delivering ML solutions for manufacturing plants at world's 4th largest automotive supplier - Built predictive maintenance models for production equipment: process parameter optimization, time series forecasting, anomaly detection - Applied LLMs for advanced text analysis on manufacturing documentation and reports - Recognized internally as Machine Learning Expert: presented methodology and results to cross-functional stakeholders and leadership

- Trained and deployed robust unsupervised anomaly detection models for real-time network traffic monitoring | Pytorch, PySpark, Docker, IoT network traffic - Published 4 papers at top ML conferences: ECML-PKDD, IEEE COINS, AINA, SINConf | Research: Anomaly Detection, Transformers, Variational Autoencoders, Extreme Value Theory - Filed 2 international patents (INPI) for IoT anomaly detection and network traffic fingerprinting - PhD thesis (CIFRE): "Robust Unsupervised Anomaly Detection", applied directly to Orange's production network monitoring infrastructure

- Conducted research on IoT device fingerprinting using time series analysis and machine learning - Published a paper at IEEE International Conference on Omni-layer Intelligent Systems (COINS 2020)

Internship in Mobile Development : * Software development of a mobile application (using AGL Windev) for the entry of site reports using GPS vehicle geolocation technology. * Use FTP protocol for the transfer of files between a client and a server on the network.