01
Data Science
Transforming complex datasets into predictive insights, intelligent models, and measurable business value.
Machine LearningDeep LearningPredictive ModelingStatistical AnalysisFeature Engineering
Stack
PythonScikit-learnPyTorchPandas
Open to opportunities
Vianney Doraboy
Data & AI Engineer
I design and develop reliable Data and AI solutions: data architecture and processing, model training, API development, and production deployment.
Data EngineeringMLMLOpsAI EngineeringLLM/GenAICloud
DATA → AI
AI ENGINEERING
Engineering flowDATA→ML→AI→Production
Python/AWS/Spark/Kafka/AI
Expertise
Building intelligent systems from data to AI.
I combine data science, data engineering, and AI engineering to design systems that move seamlessly from raw data to reliable intelligence.
02
Data Engineering
Designing reliable data platforms and scalable pipelines that turn raw data into production-ready assets.
Data PipelinesETL / ELTReal-time StreamingData WarehousingDistributed Systems
Stack
Apache KafkaAirflowSparkAWS
03
AI Engineering
Building production-grade AI systems by connecting models, data, APIs, and cloud infrastructure.
Generative AILLM ApplicationsRAG SystemsModel DeploymentMLOps
Stack
LLMsDockerFastAPIMLflow
04
Data Platforms
Engineering cloud-native architectures for analytics, observability, automation, and intelligent applications.
Cloud ArchitectureData LakesData WarehousesObservabilityInfrastructure
Stack
AWSS3RedshiftGrafana
Engineering Mindset
From experimentation to production.
01Data → Insight
02Model → Product
03Pipeline → Scale
Data Science/Data Engineering/Artificial Intelligence
Selected Projects
Turning ideas into Data & AI systems.
A selection of Data Engineering, Machine Learning, and AI Engineering projects, ranging from real-time data platforms and RAG systems to MLOps, cloud architectures, and intelligent solutions powered by simulation and optimization.
Real-Time Streaming Data Platform
Designed and developed a distributed Data Engineering platform for real-time data ingestion and processing using Apache Airflow, Kafka and Spark Structured Streaming. Implemented Avro data contracts with Schema Registry, data validation and quarantine, streaming analytics and Parquet storage on MinIO/S3. Applied production-oriented engineering with a multi-broker Kafka cluster, distributed Spark cluster, Prometheus/Grafana observability, Kafka authentication and ACLs, automated testing, Docker and CI/CD pipelines with GitHub Actions.
Production
Technologies
PythonApache KafkaApache SparkApache AirflowAvroMinIOPrometheusGrafanaDocker
Breast Cancer MLOps Platform
Designed and developed an end-to-end MLOps platform for training, evaluating, serving and monitoring a breast cancer classification model using scikit-learn. Built a reproducible ML pipeline covering data validation and preprocessing, model evaluation, experiment tracking and model management with MLflow. Developed a FastAPI inference service exposing predictions and probabilities, with Prometheus and Grafana for application and model-serving observability. Applied production-oriented engineering practices with Docker, automated unit and integration testing, and a CI/CD pipeline using GitHub Actions.
Production
Technologies
PythonScikit-learnMLflowFastAPIPrometheusGrafanaDockerGitHub Actions
AI-Powered Peacebuilding Knowledge Assistant
Designed and developed a multilingual RAG system (FR/EN) using Python, FastAPI, Pydantic, PostgreSQL/pgvector, embeddings, vector retrieval and LLM APIs (Gemini/OpenAI), with streaming responses and structured source citations. Built an end-to-end RAG pipeline and evaluation framework covering retrieval quality (Hit@K, Recall@K, MRR), groundedness, citation correctness, answer completeness and relevance, uncertainty handling and FR/EN multilingual consistency. Applied production-oriented AI/Software Engineering practices including a modular, provider-agnostic architecture, PostgreSQL/pgvector, Docker, Alembic, pytest (575+ tests), Ruff and regression thresholds for automated system quality monitoring.
Production
Technologies
PythonFastAPIPydanticPostgreSQLpgvectorGeminiOpenAIDocker
Cloud Data Lakehouse
Designed a cloud-native Data Lakehouse architecture on AWS to centralize, transform, catalog and analyze data from multiple sources. Data is stored in Amazon S3, transformed through ETL pipelines with AWS Glue and organized in a data catalog to improve data discovery and governance. Amazon Athena provides serverless analytics directly on the Data Lake, while Amazon Redshift delivers a dedicated analytical layer for Data Warehouse workloads. The infrastructure is defined and automated with Terraform to provide reproducible deployments and a scalable cloud data architecture.
Production
Technologies
AWS S3AWS GlueAmazon AthenaAmazon RedshiftPythonTerraform
Energy Digital Twin Platform
Designed a digital twin platform for monitoring, simulating and optimizing intelligent energy systems. The architecture combines real-time data acquisition, Machine Learning models and simulation mechanisms to reproduce the behavior of physical assets, analyze their operating state and anticipate system evolution. A FastAPI service provides access to data and models, MongoDB manages operational data, and Three.js enables interactive visualization of equipment and system states. The platform is containerized with Docker to provide a modular and reproducible architecture.
Research
Technologies
PythonFastAPIThree.jsMongoDBDockerMachine Learning
Renewable Energy Optimizer
Designed an intelligent engine for forecasting, simulating and optimizing renewable energy production. The solution combines Machine Learning models with TensorFlow, data analysis with Pandas and optimization algorithms to leverage historical and operational data, forecast energy production and identify more efficient operating strategies. A Digital Twin approach enables different scenarios to be simulated before implementation, while AWS services provide the infrastructure required for data storage and processing.
Research
Technologies
PythonTensorFlowOptimizationPandasAWSDigital Twin
Open to collaboration
Have a data or AI problem worth solving?
From data pipelines and machine learning systems to AI applications and intelligent digital twins.
Professional Experience
Building data-driven systems from research to production.
A professional journey across data science, software engineering, machine learning, cloud architecture, and MLOps — combining analytical thinking with production-oriented engineering.
2021 — 2026Freelance / Independent
Data & Software Engineer — Independent
Freelance, Independent & Personal ProjectsFrance
Current
Designed and developed end-to-end data and software solutions covering architecture, data engineering, machine learning, MLOps, APIs, cloud infrastructure, and deployment.
Built a conversational RAG assistant with document ingestion, embeddings, Redis Vector Search, FastAPI, LLM tool calling, Pydantic validation, and real-time SSE streaming.
Developed Qardyl, a full-stack AWS application using React, TypeScript, Python, API Gateway, DynamoDB, S3, CloudFront, Cognito, IAM, SES, and GitHub Actions.
PythonFastAPIAWSReactTypeScriptLLMRAGMLOps
2019 — 2020Fixed-term Contract
Data Scientist
EES-CLEMESSYMulhouse, France
Developed Data Science and Machine Learning solutions with a focus on statistical analysis, predictive modeling, and industrial time-series data.
Developed Machine Learning models for Fabemi to identify factors influencing vibrating press performance and predict recipe preparation times.
Contributed to SmartForest through technology selection, data platform development, and monitoring and visualization interfaces.
PythonMachine LearningTime SeriesData ScienceStatistics
Mar — Aug 2019Internship
Data Scientist
EES-CLEMESSYMulhouse, France
Developed a SmartForest proof of concept focused on anomaly detection and predictive analysis for industrial systems.
Applied Machine Learning and statistical approaches to identify abnormal operating patterns in industrial data.
Explored predictive maintenance approaches to support early detection of potential equipment failures.
PythonAnomaly DetectionPredictive MaintenanceMachine Learning
2018Academic Projects
Junior Data Scientist
Tutored Academic ProjectsVannes, France
Developed statistical and predictive models for events unrelated to communication and purchasing behavior.
Applied data analysis and statistical modeling techniques to identify patterns in historical datasets.
Worked on forecasting approaches to improve purchasing prediction and inventory management.
StatisticsForecastingData AnalysisPredictive Modeling
2017Internship
Data Analyst
Turkish Statistical InstituteIzmir, Türkiye
Performed statistical analysis and forecasting of births, deaths, and net migration using demographic datasets.
Contributed to demographic projection studies and the analysis of population trends.
Worked on urban air-quality analysis and statistical studies supporting evidence-based decision making.
StatisticsForecastingDemographyData Analysis
From data science to intelligent production systems
Data/AI/Cloud/MLOpsEducation
Knowledge built through data & technology.
An academic foundation in statistics and data science, complemented by continuous learning across software engineering, big data, artificial intelligence, and cloud technologies.
2017 — 2019
Academic Background
Vannes, France
Master's in Data Science & Statistical Modeling
Université de Bretagne Sud2017 — 2019
Advanced training in data science, statistical modeling, machine learning, data analysis, and quantitative methods.
2012 — 2017
Academic Background
Izmir, Türkiye
Bachelor of Science in Statistics
Dokuz Eylul University2012 — 2017
Training in statistics, probability, mathematical modeling, data analysis, and statistical computing.
Continuous Learning
Additional training
01
Software Development
The Web Developer Bootcamp
HTML5, CSS3, JavaScript, React, Node.js, Express, MongoDB, REST APIs and full-stack web development.
Colt Steele
02
Python Development
The Complete Python Developer
Python programming, object-oriented programming, automation, APIs, web development and software development.
Andrei Neagoie
03
Docker & Kubernetes
Docker & Kubernetes: The Practical Guide
Docker, Docker Compose, Multi-Container Projects, Deployment and Kubernetes Fundamentals.
Maximilian Schwarzmüller
Cloud Expertise
AWS Skill Builder Knowledge Badges
Knowledge badges covering core AWS concepts, architecture, core networking, serverless and data migration.
AWSServerlessAWS serverless concepts, common architectural patterns, managed services and serverless best practices.View badge
Statistics / Data Science / Engineering / Cloud
Always learning · Always buildingTECHNICAL & PROFESSIONAL EXPERTISE
Building intelligent systems from data to production
A multidisciplinary stack combining data science, machine learning, AI engineering, data engineering, cloud and software development.
I combine technical depth with an end-to-end engineering approach: transforming raw data into reliable models, intelligent applications, scalable data platforms and production-ready AI systems.
Data Science & ML
PythonSQLPandasNumPyScikit-learnPyTorchTensorFlow
LLM & AI Engineering
OpenAIAnthropicHugging FaceLangGraphLangChainMCPpgvector
Data Engineering
Apache SparkKafkaAirflow
Backend, MLOps & Delivery
FastAPIPydanticMLflowDockerpytestGitHub ActionsGit
Cloud & Infrastructure
AWS ServicesS3EMRAWS GlueAWS VPCAthenaCloudFrontLambda
Product & Web
TypeScriptReactNext.jsNode.js
01
Data & AI Architecture
Designing scalable architectures for data, machine learning and AI applications from experimentation to production.
02
Data Solutions
Building data workflows and analytical solutions that transform complex datasets into actionable insights.
03
Predictive & Machine Learning
Developing predictive models, time-series solutions, anomaly detection and optimization approaches.
04
Intelligent AI Systems
Developing LLM, RAG and generative AI systems with retrieval, tool calling and production APIs.
05
Data Platforms & Pipelines
Designing batch and streaming pipelines for reliable ingestion, transformation, processing and monitoring.
06
MLOps & Production
Automating model workflows, deployment, monitoring and reproducible machine learning environments.
07
Cloud Engineering
Designing and deploying scalable cloud solutions using AWS, containers, serverless services and managed infrastructure.
08
Software & API Engineering
Building maintainable backend services, APIs and full-stack applications around data and AI use cases.
Data/ML/AI/Cloud/MLOps/Software
From data foundations to intelligent production systems
Contact
Let’s talk about your next Data & AI project.
Have a project, research idea, data challenge, or AI system in mind? Let's discuss how data, engineering, and intelligent technologies can turn it into a reliable solution.
Send a message