You're seeing this page as if you were . The main menu is still yours, though. Exit from immersion
Clément DarnisCD

Clément Darnis

Supermalter

AI Engineer & Cloud Engineer | Python & GCP

€600/day
5 projects
Paris, FR
3-7 years

Average response time: 1 hour

Freelancer profile translated to English.
Back to original language

About Clément

AI Engineer & Cloud Engineer | RAG · LLM · FinOps · GCP/AWS ⚙️

You want to deploy aRAGsystem orLLMagents into production, but the infrastructure required to run them – and the associatedGCPor OpenAI bill – is holding you back?

Work with an engineer who wears both hats: I design your AI systems (RAG, agents, multi-model gateway, Vertex AI) AND the cloud architecture to industrialize them — deployment, scalability, security, and costs controlled onGCP / AWS.

Here's what my clients have achieved:

Club Med: Generative AI platform (RAG, multi-agents, LLM gateway via LiteLLM, LangChain, Vertex AI) in production for 2 years for Global Marketing —-50% GCP cloud costs.

Pass Culture: FinOps and cloud infrastructure redesign on BigQuery and Kubernetes —-54% storage and -86% infrastructure.

namR: ML inference infrastructure optimization on GCP (GKE, Terraform) —-80% inference costs.

Livetrend: Multi-cloud GCP ↔ AWS architecture (VPN, inter-cloud network) validated in production.

Based on your constraints (volume, latency, retrieval quality, cloud budget), I structure your AI stack and its accompanying infrastructure — RAG, agent orchestration, multi-model gateway, Terraform IaC, Kubernetes,FinOps, andMLOps.

You lead a B2B micro, small, medium, startup, or scale-up company and want to integrate AI into production without exploding your cloud bill — that's exactly my area.

An LLM/RAG system to industrialize or cloud infrastructure to stabilize and optimize? Click "Contact" and describe your situation in 3 lines, I'll respond within the hour with an initial analysis.
  • French

    Native or bilingual

  • English

    Native or bilingual

Can work on-site
Paris (up to 50km), Bordeaux (up to 50km), Lyon (up to 50km), Nantes (up to 50km), Marseille (up to 50km)

Experience

  • Club Med
    AI Engineer & Cloud Engineer | RAG, Multi-Agents
    ENTERTAINMENT AND LEISURE
    May 2023 - June 2025 (2 years and 1 month)
    Paris, France
    🎯 Mission Objective
    Design and deployment, over 2 years, of a generative AI backend platform for Club Med's Global Digital & Technology Marketing: document ingestion, full RAG, multi-agent orchestration, multi-model LLM gateway (LiteLLM), exposure of data via internal APIs, and automation of scalable cloud infrastructure with a FinOps approach.

    🔧 Achievements
    • Design and deployment of acomplete generative AI platform: document ingestion, full RAG, multi-agent orchestration, and multi-model LLM gateway viaLiteLLM2 years in productionwith the Global Marketing teams.
    • LLM monitoring and observability (Langfuse): tracking costs, latencies, generation quality, and detecting production drift.
    • Development ofPython / FastAPIAPIs to provide self-service data to business teams — containerized backend services, continuously deployed on the cloud.
    • FinOps strategy for the GCP scope:-50% cloud costswithout service degradation, including optimization of LLM inference costs (caching, batching, task-calibrated models).
    • Automation of cloud infrastructure with IaC (Terraform) and industrialization of CI/CD pipelines.

    🧰 Technical Stack

    *Backend: Python (FastAPI, uv, Streamlit), SQL, Bash

    *Generative AI: LiteLLM, LangChain, ChromaDB, Vertex AI, Flowise, Langfuse

    *Cloud & Data: GCP (BigQuery, Dataform, Cloud Run, Vertex AI, Workflows, CloudSQL)

    *Containerization: Docker, Docker Compose, Ansible

    *IaC & CI/CD: Terraform, GitLab, GitHub
    Python Artificial Intelligence RAG LLM Vertex AI
  • Livetrend.co
    Cloud Engineer | Multi-Cloud GCP/AWS & PostgreSQL
    FASHION AND COSMETICS
    March 2025 - May 2025 (2 months)
    Paris, France
    🎯 Mission Objective
    Evaluate AlloyDB (GCP) as a cost-effective alternative to Aurora (AWS) for Livetrend.co (B2B e-commerce) by replicating a realistic multi-cloud production setup, redesigning inter-cloud connectivity, and adapting backend jobs to ensure fair comparisons.

    🔧 Achievements
    • Operational inter-cloud network architecture (high availability VPN + BGP routing) to secure backend traffic between GCP and AWS
    • Deployment of a managed AlloyDB cluster equivalent to Aurora for benchmarking with an iso-configuration
    • Adaptation of backend ETL jobs (orchestrated via Prefect) to run in the new VPC + interaction with AlloyDB
    • Resolution of backend network issues (DNS, inter-VPC mounting, EFS replication) to ensure reliable data ingestion
    • Validation ofAlloyDB for productionwith a better performance/cost ratio + identification of blocking points for large-scale migration

    🧰 Technical Stack

    *Backend Data: PostgreSQL (AlloyDB, Aurora)

    *GCP Cloud: AlloyDB, Cloud VPN, Cloud Router, VPC

    *AWS Cloud: ECS, EFS, Aurora PostgreSQL

    *Network: HA-VPN, BGP, Site-to-site VPN, VPC Peering

    *Orchestration: Prefect
    Google Cloud Platform (GCP) Amazon Web Services PostgreSQL Cloud Architecture Multi-Cloud
  • REWARDPULSE
    Backend Engineer & Cloud Engineer | NestJS, GCP & Terraform
    SOFTWARE PUBLISHING
    November 2025 - May 2026 (6 months)
    Paris, France
    🎯 Mission Objective
    Industrialize the B2B multi-tenant loyalty platform RewardPulse (SaaS, GCP/NestJS): refactor a monolith into autonomous modular services, consolidate into a monorepo, replace no-code tooling, and fully secure the delivery pipeline.

    🔧 Achievements

    *Monorepoconsolidation (10+ services, 15+ shared packages) with incremental build and automated quality pipeline
    • Refactoring into modularmicroservices(Notification Gateway, Transactional Outbox, Bounded Context layout), communication via Pub/Sub
    • Shared library forpartner integrations(SFTP/API, retry, normalization),onboarding a partner in a few days
    • Custom backoffice (SSR TypeScript, HttpOnly auth, multi-tenant RBAC) replacing a no-code solution
    • GCP Terraform infrastructure (review apps, WAF, parallel DAG CI/CD) + security (Workload Identity Federation, PAM, audit logging)

    🧰 Technical Stack

    *Backend: NestJS, TypeScript, Prisma, Drizzle, oRPC, Zod

    *Architecture: Microservices, Pub/Sub, Outbox Pattern

    *Frontend: TanStack Start (SSR), React, Vite

    *Cloud: GCP (Cloud Run, Cloud SQL, Pub/Sub, BigQuery, GCS, IAM)

    *IaC: Terraform, Terraform Cloud

    *CI/CD: GitLab CI, review apps
    Backend Development NestJS Google Cloud Microservices Terraform

Reviews

5.0

Out of 2 ratings

A

Alexis

Napta

Reviewed on 11/17/2025

Clément quickly grasped our subject, which was not trivial, and asked the right questions, providing us with avenues that helped us move forward, which is what we expected.
L

Lucile

Pass Culture - Pôle Tech

Several months project

-

Reviewed on 11/6/2025

Clément supported us on multiple topics within the team. He is an excellent data engineer, both technically skilled and a great communicator. He provides the necessary visibility on the progress of his work, which facilitates coordination with other teams. He demonstrated real added value on several key subjects, particularly in reducing infrastructure costs and simplifying our data stack (Airflow, GCS, etc.). His interventions helped rationalize our pipelines while improving the reliability and maintainability of our platform. A reliable, rigorous, and impact-oriented professional, whom I recommend without hesitation.

Recommendations

These freelancer profiles also match your criteria

AgathaA

Agatha Frydrych

Backend Java Software Engineer

4.7

(3)

2

BaptisteB

Baptiste Duhen

Fullstack developer

4.6

(4)

5

AmedA

Amed Hamou

Senior Lead Developer

4

(2)

7

AudreyA

Audrey Champion

Web developer

4.3

(3)

4

Education

  • Engineering Degree, Generalist
    Ecole Centrale de Marseille
    2022
    Diplôme d'ingénieur, Généraliste

Skill set

Categories