About Henri
I help companies turn tabular, structured data into real-time business value. From architecture to deployment, I design low-latency, production-ready solutions that scale.
Core Expertise
Real-Time & Streaming Pipelines
Apache Flink, Kafka MSK, Spark Structured Streaming, AWS Kinesis
Machine Learning & Feature Engineering
Python, scikit-learn, XGBoost, LightGBM, TensorFlow, AWS SageMaker
Data Engineering
AWS Glue, Redshift, S3, Lambda, Step Functions, PostgreSQL, MySQL, Redis/Valkey, feature stores
Infrastructure & DevOps
Docker, Kubernetes, Terraform, AWS IAM & cross-account security
CI/CD & MLOps
I build or upgrade continuous-integration / continuous-delivery pipelines to make model releases and data-pipeline deployments automated and reproducible.
Technologies: GitHub Actions, GitLab CI, AWS CodePipeline/CodeBuild, automated testing with pytest.
Engagement
Flexible and autonomous, I integrate quickly with teams or run full projects end-to-end—covering architecture, feature engineering, model training, deployment, and ongoing monitoring.
French
Native or bilingual
English
Native or bilingual
Remote only
Primarily works remotely
Experience
- Capitec BankMachine Learning EngineerBANKING AND INSURANCEDecember 2024 - Today (1 year and 6 months)Le Cap, South AfricaRisk Department – South African Bank, Fraud Detection:- Deployed a Recurrent Neural Network (RNN) model into production, scoring 10 million accounts daily- Designed and implemented a real-time Flink pipeline, processing 50+ transactions per second- Built end-to-end client risk assessment models from the ground up, covering data preparation, feature engineering, and deployment
- Capitec BankData EngineerBANKING AND INSURANCESeptember 2022 - December 2024 (2 years and 3 months)Le Cap, South AfricaData Engineer for South Africa Bank:- Engineered scalable ETL pipelines processing 20M+ rows daily into Amazon RDS (MySQL) using AWS Glue, S3, and Lambda.- Administered AWS environment (IAM, VPC, CloudWatch, S3, RDS, Lambda) for 20 engineers, ensuring cost efficiency, observability, and compliance.- Implemented CI/CD pipelines with GitLab Runner, CodeBuild, and Terraform to automate deployment of Glue Jobs, Step Functions, and Lambdas.
- Hoorah GroupData ScientistTELECOMMUNICATIONSJanuary 2020 - September 2021 (1 year and 8 months)Marketing Digital AgencyEstablished and led the formation of the Data Department by delivering:- ETL Pipeline for Google BigQuery – built with Google Apps Script to automate ingestion and transformation of marketing performance data.- Custom Instagram Scraper – engineered a tool to extract and process public profile and engagement data, enabling advanced audience segmentation and insights for client strategy sessions.- Automated BI Reporting – developed dynamic dashboards and scheduled reporting workflows, reducing manual effort and improving reporting efficiency by 70%.
Reviews
Recommendations
FU
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
- Msc in Data Analytics and Business IntelligenceEDHEC Business School2019Objectives : Understanding the tech environment by intensively practicing coding. Classes : Statistics, Data mining, machine learning, Business analytics, Project management, Data Visualization, Web Analytics... Languages learnt : HTML, CSS, JS, R, ruby, python, SQL.
- Fullstack Developer, Web Development (#Bach 177)Le Wagon20189-week intensive coding bootcamp learning HTML, CSS, Bootstrap, JavaScript, jQuery, SQL, git, GitHub, Heroku and Ruby on Rails.
Certifications
- AWS Certified Machine Learning EngineerAWS2024
- AWS Certified Solutions Architect - AssociateAWS2023