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

Thomas M.

AI, Devops Linux, Kubernetes

€800/day
Plaisir, FR
15+ years

Average response time: 1 hour

Freelancer profile translated to English.
Back to original language

About Thomas

With 25 years of expertise in systems and network administration (Linux, databases, Kubernetes orchestration), I am now dedicated to implementing generative AI infrastructures, specializing in the deployment and optimization of LLM models locally (on-premise) or hybrid (cloud).

I offer a turnkey solution for companies wishing to:
✅ Deploy local LLMs (Mistral, Llama, etc.) or cloud (OpenAI, Anthropic, etc.) via a unified architecture based on an OpenAI-compatible proxy (LiteLLM).
✅ Centralize access to models through user interfaces (LibreChat, Open WebUI, or custom interfaces like chainlit) or directly via API, with quota management, logging, and monitoring.
✅ Secure and optimize costs by combining open-source models (self-hosted) and cloud services, according to business needs.

Why choose this approach?
  • Data Sovereignty: Local hosting of sensitive models.
  • Flexibility: Seamless switching between local and cloud models.
  • Controlled Cost: Resource optimization (GPU, inference servers).
  • Compatibility: Native integration with existing tools (standard OpenAI API).

Technical Environment:
  • AI Infrastructure: LiteLLM (proxy), LibreChat, Ollama, vLLM, FastAPI, LangChain, chainlit.
  • Models: Mistral, Llama, Mixtral, Phi-3, as well as cloud APIs (OpenAI, Anthropic, etc.).
  • DevOps/Orchestration: Kubernetes, Ansible, GitLab CI, Terraform.
  • Databases: PostgreSQL, Vector DB (Weaviate, Qdrant, PGVector).
  • Historical Foundation: Linux (all distros), Oracle, MariaDB/Galera, JBoss, Tomcat.

At your service for:
  • Auditing your generative AI needs (use cases, technical/regulatory constraints).
  • Designing a suitable architecture (full on-premise, hybrid, or cloud).
  • Supporting your teams in the use and administration of LLMs.
  • French

    Native or bilingual

  • English

    Native or bilingual

Can work on-site
Plaisir (up to 50km), Plaisir (up to 40km), Paris (up to km)

Recommendations

Be the first to recommend Thomas

Help this freelancer shine by sharing your experience working together.

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

  • Management Information Systems BTS
    Pau
    1999
    Spécialisation Systèmes & Réseaux

Skill set

Categories