Dorsaf Sdiri

Senior Data Engineer/ML Engineer

Salaire / Taux journalier

93310 Le Pré-Saint-Gervais, France

Freelance

Expertises

PythonGoogle Cloud PlatformNLP / Natural Language ProcessingApache SparkApache AirflowPySparkGitHubDatabricksAzureETLTerraformSnowflakeRequêtes SQLFlaskPyTorchFirebaseScrapingScalaHadoopKafkaCRMTensorFlowLinuxData AnalysisRData Miningscikit-learn

À propos

Introduction

I am a Data & Machine Learning Engineer with 7 years of experience developing the backend of AI applications and data pipelines. I work autonomously across the full lifecycle, from data collection and large‑scale processing to modeling, deployment, and monitoring, and I enjoy taking ownership of technical choices around Big Data frameworks and architectures. I have solid understanding of statistical models, associated with Big Data Analytics , Cloud services and ML pipelines. I’m passionate about MLOps, DataOps, and DevOps topics, with a deep interest in technology, automation, and building reliable production systems. With a background in statistics, I have a strong command of machine learning, deep learning, and data analysis methods. I've worked in several sectors like CRM, Media, Fintech, Cyber security, Marketing, recrutement and psychology , and led several machine/deep learning projects. My main objective is to grow in a stimulating, fast‑paced environment, working on interesting and impactful projects alongside data scientists, analysts, engineers, and cross‑functional teams, where I can create real value and contribute to innovation. github link: https://github.com/Dorsaf-Sdiri

Liens

Expérience de travail

Data Engineer

OVHcloudFreelance

AirFlow, PySpark ,Python, Github ,CI/CD

ML/Data Engineer

Publicis Media

sept. 2022 - déc. 2024

2 ans 4 mois

Paris, France

terraform/ GCP / Snowflake / Python/ SQL

Data Engineer/ Scientist

Medix™Freelance

juil. 2021 - mai 2022

11 mois

Data Scientist

TalentodayFreelance

juil. 2021 - mai 2022

11 mois

Machine Learning Engineer

déc. 2020 - mars 2021

4 mois

*Design, development and deployment of the back-end of a lead generation tool using NLP algorithms and AI for a client company Keywords: Python, Flask APIs, app engine (GCP), NLP, TF-IDF, Bi-LSTM and attention models using Pytorch, Scoring with Catboost, Firebase, Cloud Scheduler, cron jobs, scoring models, Twitter developer API, scrapping, feature engineering and extraction

Data Scientist/Engineer

Venari Security

juin 2019 - déc. 2020

1 an 7 mois

Big Data training

Data vectis

mars 2019 - mai 2019

3 mois

Hortonworks frameworks: Ambari, Spark, Scala, Hadoop, Kafka,HDFS, yarn, IntelliJ, SBT, unit tests

Data Scientist

Kaoun - كَوْن

sept. 2018 - mars 2019

7 mois

Soliman, Tunisie

Data scientist intern

Business & Decision

févr. 2018 - juil. 2018

6 mois

Soliman, Tunisie

Web Usage Mining: Traceability of the navigation Path of Internet users in the aim to personalize publicity. • Preprocess web server logs ( PCAP files) • Find the most frequent trajectories by detecting communities of a dynamic graph using DSBM (Dynamic Stochastic Blockmodels) • Sequence clustering with Hierarchical clustering using the optimal matching and Co-clustering technique. • Built predictive models for User profile (decision trees) and Website (Association rules & sequential pattern). • Validate the clustering (ICL criterion , Rand Index, Silhouette Index). • Web Content mining: Scraping the content of Websites, applying text mining preprocessing and topic modeling using Latent Dirichlet Allocation LDA • Matching between Website clusters and User's profiles • Exploratory analysis, multivariate analysis (PCA and correlation study ) and graph visualization(dynamic and static) Keywords: Behavioral Analysis, profiling, segmentation, CRM, Social Networks, Web graphs, Recommender system, dynamic and temporel graph

Deep learning Intern

Institut Pasteur de Tunis - معهد باستور تونس

juin 2017 - août 2017

3 mois

Tunisie

Music genre classification using convolutional neural network CNN on mel-spectogrammes after processing the signals using Python/TensorFlow/librosa/ffmpeg. Keywords: Supervised learning, sound data


Formation

École Supérieure de la Statistique et de l'Analyse de l'Information

Engineer's degree in Statistics and Data Analysis

Preparatory Institute of Engineering Studies of El Manar

Pre-Engineering cycle in Mathematics and Physics

Bourguiba Pioneer Secondary School of Tunis

Mathematics Baccalaureate


Licences et certifications

Exploring ​and ​Preparing ​your ​Data with BigQuery

Délivré le : juil. 2022

Certifié par Coursera

Creating New BigQuery Datasets and Visualizing Insights

Délivré le : juil. 2022

Certifié par Coursera

Le meilleur endroit pour trouver votre prochaine opportunité

© 2026. Tous droits réservés.