Hello, I’m
Ghazi Ben Dahmane
Engineering leader building enterprise AI platforms.
Open to advising & speaking
6,500+ Enterprise Users Active across Amundi business lines
200 GB Daily Log Volume High-throughput Go & S3 LLM Gateway
15+ Production Services Conversational AI, RAG & DeepSearch
25 Engineers Led R&D architecture, delivery & hiring
About
I’m a software engineer and Head of R&D with more than a decade of experience turning complex systems into products people can depend on.
Today I lead the architecture and delivery of Amundi’s AI platform: 15+ services supporting 6,500 users across LLM gateways, RAG systems, knowledge tooling, APIs, and product experiences.
My work sits where platform engineering, AI adoption, and technical leadership meet.
Selected work
All projects 01 ALTO Studio Enterprise AI platform bringing conversational AI, RAG, research, document workflows, and reusable APIs into one governed product. 6,500 users across Amundi 02 Enterprise LLM Gateway A high-throughput Go gateway for multi-provider routing, streaming, quotas, cost accountability, and operational visibility. 200 GB of logs processed daily 03 AI Adoption & Enablement Reusable APIs, web components, documentation, and engineering practices that let product teams add AI without rebuilding the platform. Shared integration patterns 04 Knowledge & MCP Platform A central MCP catalog and multi-source knowledge pipeline for enterprise agents, with semantic processing and hybrid retrieval. Confluence, Jira, and document sources
Recent writing
All articles Enterprise RAG at Scale: The Complete Engineering Guide A practical, end-to-end series for building multilingual, secure, measurable retrieval-augmented generation systems that survive production traffic. Enterprise RAG · LLM Platforms Building Production RAG: Reference Architecture and Rollout Playbook Assemble ingestion, hybrid retrieval, reranking, grounded generation, evaluation, and operations into a deployable API with a staged enterprise rollout. Enterprise RAG · Reference Architecture Operating Enterprise RAG: Security, Observability, SLOs, and Cost Secure and operate RAG with retrieval-time authorization, prompt-injection defenses, trace-level observability, freshness SLOs, cost controls, and incident playbooks. Enterprise RAG · Security
Experience
Full CV- 2025 — Now Head of ALTO Studio R&DAmundi · Paris
- 2021 — 2024 Full Stack EngineerAmundi · Paris
- 2021 Full Stack EngineerThink-it · Remote
- 2020 — 2021 Software EngineerHexastack · Tunis
- 2020 Full Stack EngineerFinaxys · Paris
Let’s connect
Working on an AI platform, a difficult systems problem, or engineering-team scale? More about me →