Freelancer profile translated to English.
Back to original languageAbout Souleymane
General Engineer graduated with a Master's degree in Fundamental Mathematics, specialized in Data Engineering/Science. I position myself as an expert in the industrialization of Data and AI systems. My passion is to transform complex problems into robust, high-performance, and production-ready solutions.
I am a Freelancer/Consultant, available for strategic missions around Data Stack modernization, MLOps, Analytics Engineering, and Generative AI integration.
I have participated in several significant projects:
Axio Conseils: Auto claims prediction pipeline, integration via Streamlit, Docker deployment, and CI/CD.
EHDI Technologies: Banking fraud detection, integration via Flask API, and PostgreSQL management.
Generali France: Optimization of ETL pipelines and automation of contract extractions for the Data & Actuarial team.
I recently obtained my dbt certification, strengthening my expertise in data modeling and transformation. I also developed a Vanna SQL LLM for query interpretation and published a comprehensive tutorial on dbt. My portfolio showcases my achievements in PySpark, CI/CD, and automation.
Data Engineering: ETL, Spark, AWS (basics), dbt, CI/CD with GitHub Actions.
Automation & QA: pre-commit, Makefile, pytest, pyproject.toml, pre-config.yml..
Databases: SQL, BigQuery, Oracle, MySQL, PostgreSQL.
Machine Learning: regression, classification, prediction.
Languages: Python, R, PySpark.
Backend & API: Flask REST-API, Streamlit
Generative AI: LLM with Vanna SQL
Visualization: Streamlit, Plotly, interactive dashboards.
Analysis and valuation of your data.
Implementation of reproducible and auditable pipelines.
Development of ML models tailored to your business needs.
Comprehensive automation and documentation to ensure quality and reliability.
French
Fluent
English
Conversational
Wolof
Native or bilingual
Can work on-site
Ermont (up to 50km), Paris (up to 50km), Paris 10e Arrondissement (up to 50km)
Experience
- Banque de DakarExperienced Data EngineerBANKING AND INSURANCEApril 2022 - February 2026 (3 years and 10 months)Design and maintenance of PySpark/SQL pipelines (ingestion -> transformation -> usable tables) for BI/analytics purposes.• Optimization of processing (reduction of run time, volume management): filters, partitioning, Spark tuning.• Data quality: checks (completeness, consistency), automated test suites, traceability, and standardization of jobs.• Collaboration with BI/IT teams: needs clarification, model adaptation, iterative delivery.Stack: Python, PySpark, SQL, PostgreSQL/Oracle, Hadoop (HDFS), Docker, Git, CI/CD, pytest
- AxioConseilsData Engineer / ML EngineerDIGITAL AND ITMarch 2021 - April 2022 (1 year and 1 month)Paris, FranceDesignand implementation of aPOCto anticipate and predict automotive claims risks
- Setting up the processes to properly start the project
- Datapreprocessinganddevelopment of claims prediction models(LightGBM), achieving anF1-scoreof0.9
Environment: Python, Pandas, Scikit-learn, Streamlit, Docker, PostgreSQL,Git, Makefile, pre-commit - eHDI TechnologiesData EngineerDIGITAL AND ITJanuary 2020 - February 2021 (1 year and 1 month)Paris, France
- Mapping of data sources and flows for a European energy company
- Analysis of data quality (completeness, consistency, duplicates) and definition of data quality KPIs.
- Development of an improvement roadmap aligned with the target data & analytics trajectory (architecture, governance).
Environment: Python , Pandas, PostgreSQL/Oracle, Git
Reviews
Recommendations
Be the first to recommend Souleymane
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- General Engineer specialized in Information Systems - Data Science TrackIMT- ATLANTIQUE2019Le filière data science forme les futurs ingénieurs de l'IA sur les concepts et techniques indipensables pour bien mener un projet en data. J'avait le choix de 5 formations qui sont: - Machine Learning et Statistiques( Principes et Fondamentaux des algos, Méthode d'optimisation, tests d'hypothéses, etc...) - Business Intelligence (TALEND, TABLEAU) - Data Mining (EDA python, CRISP-DM) - Computer Vision avec Open-CV ( Tracking objects, Etude avané de l'image) - Deep Learning (MLP, Carte de koenan)
Certifications
- Coursera Machine Learning CertificateCoursera2018
- Big Data FundamentalsFun-Mooc2019