Data & AI Engineer

I turn raw data into pipelines, models,
and products people use.

Scroll

01 · About

Data & AI Engineer at Airbus, building LLM-based quality analysis systems and ML pipelines for the A330/A350 programs. GCP Professional Cloud Architect & Data Engineer certified.

I work at the intersection of data engineering and AI, from data pipelines to fine-tuned LLMs to GenAI products, all in service of one thing: making data useful.

Outside of work, I build CraftCourse, an AI-powered learning platform with 500+ users.

Hamza El Belghiti

02 · Skills

Tools I reach for

Programming

PythonJavaC

AI & ML

PyTorchScikit-learnLangChainHuggingFaceRAGMLflowCrewAIn8nLangGraphFine-tuningMLOps

Databases

BigQueryPostgreSQLSupabaseRedispgVectorMongoDBOraclePineconeChromaDB

Web Development

ReactNext.jsTypeScriptREST APIsFastAPIDjangoStreamlit

Cloud

Google CloudAWSSkywise

Tools

LinuxDockerGitGitHub ActionsJiraClickUp

Certifications

GCP Professional Cloud Architect

Google · 2026

GCP Professional Data Engineer

Google · 2024

dbt Fundamentals

dbt Labs · Nov 2023

Apache Airflow

Astronomer · 2023

Data Scientist

DataCamp · 2022

Machine Learning with Python

freeCodeCamp · 2022

03 · Experience

Where I've worked

Data & AI Engineer

Sep 2025 – Aug 2026

Airbus · Toulouse, France

  • Maintained and evolved a dashboard centralizing QLB customer quality data for the A330 and A350 programs.
  • Accelerated the identification of recurring quality non-conformities by developing an LLM-based analysis system for QLBs from final cabin presentations.
  • Reduced quality teams' manual search time by designing a RAG pipeline that classifies QLBs from their description, automatically retrieving the applicable acceptance criteria (reference, page, conditions) and status (acceptable/non-conforming).
  • Designed an end-to-end ML pipeline using XGBoost to predict customer presentation dates at the A330/A350 FAL, achieving a MAE of 4.1 days and 87% of predictions within ±7 days, improving team planning and resource allocation.
SkywisePythonPySparkNLPGeminiPrompt EngineeringXGBoost

Analytics & AI Engineer

Feb 2024 – Jul 2025

Blent.ai · Paris, France

  • Implemented automated ELT pipelines feeding the Customer Data Platform, integrating 5+ sources.
  • Developed Reverse ETL flows for marketing tools such as HubSpot and CustomerIO, enabling the marketing team to target campaigns on customer segments updated daily instead of manually.
  • Unified client reporting by building sales and marketing dashboards analyzing customer KPIs for a 5-person team.
  • Developed an AI chatbot to assist students on the platform and automated the grading of student projects using a RAG system.
  • Consulted and designed an AI MVP for the DGAC to automate the extraction and monthly structuring of data from 300 French aerodromes using an LLM.
AirbyteMageAirflowBigQuerydbtMetabaseLookerMongoDBHubSpotOpen MetadataLangchainHuggingFaceGroqMistralPineconePDFplumberOpenAI APIChromaDBStreamlit

Machine Learning Engineer

Jun 2023 – Sep 2023

3D Smart Factory · Mohammedia, Morocco

  • Reduced infrastructure costs by 98% ($85/month to $1.3 per 1,000 requests) by deploying a deep learning model for 3D tooth segmentation via a serverless architecture.
  • Delivered an interactive 3D visualization interface for exploring tooth segmentations, integrating 3D libraries.
ViteReactTailwind CSSThree.jsVTK.jsFirebaseFastAPIDockerVercelAWS

04 · Projects

My work

CraftCourse

AI-powered learning platform (500+ users)

CraftCourse

AI-powered platform generating personalized learning roadmaps, with a real-time AI tutor and full gamification system.

Next.jsSupabasepgvectorGemini APIHetzner VPSStripe
PixelWallet

Web app

PixelWallet

Secure gaming wallet for minors that lets young players manage in-game purchases with parental controls and spending limits.

ReactNext.jsVercel
TeethSeg

AI / 3D web app

TeethSeg

3D tooth segmentation, deployed serverless on AWS, cutting cost from $85/mo to $1.3/1k requests.

ReactThree.jsFastAPIAWS Lambda
Decathlon Chat

AI chatbot

Decathlon Chat

Customer service chatbot trained on Decathlon Morocco data using RAG architecture for accurate, context-aware responses.

StreamlitLangchainChromaDBOpenAI API
GPTube

AI app

GPTube

YouTube video summarizer and Q&A using Whisper transcription, LangChain retrieval, and a Streamlit UI.

WhisperLangChainStreamlit
BrandGenie

Web + AI

BrandGenie

AI branding assistant powered by OpenAI GPT-3 that generates brand names, slogans, keywords, and advertising copy for businesses.

ReactOpenAI GPT-3ViteVercel
Course Recommender

ML system

Course Recommender

Coursera recommendation engine using BERT embeddings, MLflow experiment tracking, served via FastAPI.

BERTMLflowFastAPIPython
NYC Taxi Analytics

Data engineering

NYC Taxi Analytics

NYC taxi records analysis using Mage ETL, GCP Storage, BigQuery data modeling, and Looker Studio dashboards.

MageBigQueryLooker Studio
Data Engineering Jobs

Data analytics

Data Engineering Jobs

Analyzing the Data Engineers job market in the USA and predicting salaries with ML models trained on Glassdoor data.

PythonStreamlitScikit-learnPandasPlotly

06 · Contact

Let's work together

Prefer email? Reach me directly at hamza.lbelghiti@gmail.com

Elsewhere

Toulouse, France