ENSO
One AI platform, four products, one set of rules
Lead architect of the shared platform behind four AI product capabilities, from model access to agent actions.
- Amazon Bedrock
- Aurora PostgreSQL
- pgvector
- EKS
- Keycloak
- MCP
Work
Case studies
Six engagements, told by the problem, the decisions and the outcome.
Inserm
One software factory for 12 teams
40+ projects on automated CI/CD and 50% fewer manual interventions, on HDS-compliant infrastructure.
- GitLab Enterprise
- Nexus
- SonarQube
- Kubernetes
Volkswagen Group
99.9% availability, by design
Multi-AZ AWS infrastructure defined as code, ensuring 99.9% availability for the GENWIN web platform.
- AWS
- Multi-AZ
- Infrastructure as code
- Clean Architecture
SNCF
A data marketplace with 90,000 users
Spring Boot microservices on managed GCP services, with observability built in from the start.
- Spring Boot
- Microservices
- Google Cloud Platform
- Managed services
APHP
Cutting patient email response time by 70%
Vespa AI vector search cut email response time by 70% on a medical follow-up platform built with LLMs and RAG.
- LLMs
- RAG
- Vespa AI
- Vector search
Magik AI
Open-source AI on a GPU cluster
An interactive media generation platform running open-source models on a RunPod GPU cluster, with GenAI pipelines, agents and n8n workflows.
- RunPod
- Open-source models
- RAG
- Fine-tuning
Last updated:
Got an AI project stuck between demo and production?
Tell me what you are building. After a first conversation you will know whether I can help and what I would do first.
+33 6 02 73 49 22 me@osmanrami.fr