Freelance Développeur Fullstack Python, Expert Cloud AWS et Architecte de solutions d'IA agentique, ex-CTO et Docteur en Neurosciences, I help my clients design and deploy technological solutions scalable, robust and intelligent. My expertise covers développement d'applications web et mobiles, l'architecture cloud serverless sur AWS, l'orchestration d'agents IA, les pratiques DevOps modernes et la Data Science appliquée. J'interviens de bout en bout : de l'analyse des besoins à la mise en production, en intégrant des assistants IA sur mesure, des workflows agentiques et des infrastructures cloud pensées pour l'automatisation et la montée en charge.
References
Emiliano Macaluso, Université de Lyon, France
Eric Sanchez, Université de Genève, Suisse
SKILLS
- Python | JavaScript
- AWS Cloud | Serverless | MLOps
- Pydantic AI | Strands Agents | LangChain
- Hermes Agent | Custom Agents
- AgentCore | LangGraph Platform
- Bedrock | OpenRouter | Vertex AI
- Logfire | Langfuse
- IaC | Terraform | CloudFormation
- Web | Django | React
- API | Ninja | FastAPI | DRF
- SQL | PostgreSQL | NoSQL
- IA | PyTorch | Scikit-learn
- Streamlit | Plotly | Dash
- Git | GitHub | GitLab
- Scaleway | Infomaniak | Cloud Souverain
LANGUAGES
Strengths
- Determination
- Troubleshooting
- Sociability
- Autonomy
Hobbies
Cloud Expert AWS
MLOps & Agents IA
Fullstack Developer Python
Samy A. Foudil
Professional experiences
MLOps freelance mission: design, deployment and industrialization of intelligent solutions for automated processing of complex documents for the French energy company.
- Design and industrialization of ML pipelines for the automatic analysis of documents (PDF, images, forms).
- Design of AI Agents specialized in document processing (Textract, Rekognition, ADK, AgentCore).
- Déploiement, automatisation et monitoring de modèles sur des architectures cloud scalables (Lambda, Stepfunctions, DynamoDB).
- Mise en œuvre de mécanismes d'alerte et de supervision en production pour assurer la robustesse des systèmes (CloudWatch, SNS, SQS).
- Force de proposition dans la résolution de problématiques complexes liées à l'automatisation.
NeuRoam project: platform for collecting and analyzing behavioral data from daily life.
- Full-stack development of a web application, APIs and a mobile application (NeuRoam).
- Integration of AI models for extracting spatio-temporal insights from geolocated data.
- Setting up CI/CD pipelines with GitHub and Docker.
- GDPR compliance and CNRS requirements for health data management.
- Training and support for users for the adoption of the platform.
Projet BrainWatch : conception d'une IA pour interpréter le comportement humain (Deep Tech, CIR).
- Obtaining non-dilutive financing (CIR, French Tech, BPI).
- Design of a scalable AI infrastructure for data-driven management.
- Development of BrainWatch, a multimodal behavioral analysis platform.
- Implementation of automated CI/CD pipelines, GDPR compliance.
- Optimization of data processing pipelines on AWS.
AGPA project: research on the neural bases of agent vs. patient social representation.
- Deployment of ML and DL models for fMRI and EEG data.
- Analysis of millions of voxels for the study of brain-behavior interactions.
- Processing complex multimodal time series.
Research project: modeling episodic memory mechanisms in virtual reality.
- Analysis of fMRI and behavioral data (millions of data points).
- Development of a mobile data collection application.
- Web interface for visualizing experimental results.
- Deployment of a hybrid cloud infrastructure (AWS + CRNL).
- Publication of 3 scientific articles promoting the results.
HUBBLE Learn project: behavioral observatory based on e-learning traces.
- Collection and analysis of behavioral data from medical students.
- Evaluation of the impact of teaching strategies on learning.
- Design of interactive dashboards and dedicated database.
Tamagocours project: digital game to raise awareness of the educational uses of digital technology.
- Analysis of the dynamics of serious game appropriation via the processing of traces.
- Clustering and ML application to segment user behavior.
- Recommendations to optimize the experience and educational impact.
LENA project: validation of a voice recognition system for young children.
- Processing and analysis of the oral productions of French-speaking children.
- Development of robust NLP models adapted to children’s specificities.
- Scientific validation of the system in a research and therapeutic framework.
ASTERISK project: deployment of an IPBX for CPAM telecom management.
- Deployment of an IPBX solution (Asterisk) for CPAM agencies.
- Network optimization (routers, VLANs) and VMware virtualization.
- Technical support and maintenance of network and telecom infrastructures.
Education & Training
PhD Cognitive neuroscience
University Lyon 1 Claude Bernard
Master's degree in Applied Cognitive Sciences
Lyon 2 Light University
Bachelor's degree in Applied Cognitive Sciences
Lyon 2 Light University
BTS Computer Science
La Martinière Duchère Lyon
Research publications
-
2024"The influence of the precuneus on the medial temporal cortex determines the subjective quality of memory during the retrieval of naturalistic episodes"Scientific Reports, 14 (1), 7943. DOI
-
2021"Memory for spatio-temporal contextual details during the retrieval of naturalistic episodes"Scientific Reports, 11 (1), 14577. DOI
-
2020"Context-Dependent Coding of Temporal Distance Between Cinematic Events in the Human Precuneus"Journal of Neuroscience, 22(1), 101-123. DOI
-
2015"Reliability of the Language ENvironment Analysis system (LENA™) in European French"Behavior Research Methods Volume 48, pages 1109–1124. DOI