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

Arthur Hirel

AI Engineer - Agentic Systems Security

€750/day
Paris, FR
3-7 years

Average response time: 1 hour

Freelancer profile translated to English.
Back to original language

About Arthur

I design and deploy applied AI systems capable of reliably interacting with complex business environments. My work lies at the intersection of artificial intelligence, software engineering, and product, with a focus on AI agents, neuro-symbolic systems, and their integration into real-world applications.

I am involved in the entire value chain: designing agent architectures, RAG and GraphRAG pipelines, integration with business tools, implementing safeguards like human-in-the-loop control and granular permissions, as well as reliability, monitoring, and observability topics. My goal is to build useful, robust, and scalable AI systems.
  • French

    Native or bilingual

  • English

    Native or bilingual

Remote only
Primarily works remotely

Experience

  • Granular Software
    Co-founder in charge of product and technology
    TECH
    September 2025 - Today (9 months)
    Paris, France
    Co-founder and technical leader of a platform enabling B2B software publishers to design reliable and secure AI agents for their clients.

    Work on domain modeling, action surfaces, permissions, validations, runtime control, and product integration, to make agentic experiences truly operational in production.
    AI Safety AI Agent Ontologies Typescript Tech Lead
  • mcpresso
    Co-founder of an open-source library for securing MCP servers
    TECH
    January 2025 - September 2025 (8 months)
    Paris, France
    Design of an open-source TypeScript framework for building robust, production-ready MCP servers around existing APIs. Work focused on OAuth 2.1 authentication, single and multi-user models, interoperability with real stacks, and the primitives needed to make business systems exposable to agents.
    Typescript MCP software architect Ontologies
  • Granular Software
    Development of neuro-symbolic architectures for reliable agentic systems
    TECH
    June 2020 - Today (6 years)
    Paris, France
    Construction and deployment of various neuro-symbolic systems, enabling better interaction of AI agents with applications with complex logic (accounting, granular permissions, human control, etc.).

    Work on the main AI agent development technologies (LangChain, LangGraph, LlamaIndex, RAG, GraphRAG, etc.), as well as the components needed for their production deployment: orchestration, session management, tool-use action execution, data ingestion and retrieval, monitoring, and observability.

    Design of platforms and tools for modeling complex business domains, guiding agent behavior, and making their actions more reliable, traceable, and actionable in real environments.
    AI Safety AI Agent artificial intelligence

Recommendations

Be the first to recommend Arthur

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

Skill set

Categories