Senior AI & Solution Engineer with 9+ years of experience designing secure systems and driving AI strategy. I lead POCs through to production and deploy responsible AI in regulated environments (SOC 2, GDPR), turning complex technical concepts into clear business value for non-technical stakeholders.
Fig. 2. 420 contributions, Sep 14, 2025 – Sep 16, 2026. Source : GitHub.
Taking a POC all the way to production instead of leaving it as a demo. RAG systems over sensitive data, autonomous agents exposed over MCP, fine-tuning and deployment of open-source models — Mistral, Llama — including fully on-premise setups.
RAG systems · Autonomous agents · MCP · Open-source models
Designing for regulated environments from day one. Applied cryptography, zero-trust architecture, anti-phishing detection, risk analysis, and automation of SOC 2 and GDPR compliance audits.
SOC 2 · GDPR · Cryptography · Anti-phishing · Zero-trust
Turning a business need into an architecture that holds up under both load and audit. PSD2 open banking, national customs systems, API marketplaces, real-time chains on Kafka and RabbitMQ — domains where a design mistake is expensive.
Distributed systems · Event-driven architecture · Kafka · APIs · Cloud · Regulated industries
Leading teams of up to ten developers, running technical interviews, setting standards. And above all: making a technical decision understandable and defensible in front of non-technical stakeholders.
Tech lead · Hiring · Stakeholder communication · Product scoping
Passbolt — Open-source password management solution used by governments and large organizations
Switch Case — Generative-AI products, automated security and large-scale RAG
ColartBe — End-to-end delivery for European institutions, startups and SMEs
Miind — National customs delivery system
Luxhub — Open-banking infrastructure for financial institutions
Positive Thinking Company — Investment fund calculation and ingestion systems
Designed and deployed a large-scale RAG agent built on open-source models (Mistral AI) and vector databases.
No outbound calls: all processing stays on-premise, embeddings included, on infrastructure the client administers itself. GDPR compliance is structural, not declarative.
The difficulty is shape, not volume: millions of medication rows in CSV on one side, a written rules document on the other, to be crossed before a reimbursement can be decided.
Escalation to a human expert on the cases the model cannot settle. Every release first goes through a parallel test pipeline checking answers against defined rules.
Architected a self-hosted video conferencing platform for entrance exams and remote teaching: no data leaves the Commission’s infrastructure, up to 300 participants per call.
Designed the whole system, server architecture plan included. Real-time messaging on RabbitMQ, event-driven, with a browser client served from the Commission’s own page.
Bilingual static site generated from markdown files validated by a Zod schema.
Every push to main triggers the build and publish. A print stylesheet produces
a clean PDF from the same source.