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

Alix Caperan

AI Developer - Full stack

€350/day
1 project
Paris, FR
3-7 years

Average response time: 1 hour

Freelancer profile translated to English.
Back to original language

About Alix

My name is Alix and I am currently a computer science student at the University Paris-Dauphine of the PSL group.
In parallel with my studies, I work as a freelancer specializing in artificial intelligence.

Key skills:

-AI application development: AI-assisted content creation platforms, custom GPT-based search engines, etc.

-Business integration: using AI for customer support, human resources, strategic monitoring, and document analysis.

-Automation of complex workflows using AI

-Expertise in semantic and vector search (FAISS, Qdrant, Pinecone)

-AI API development (FastAPI, LangChain) and deployment on the cloud or locally
  • French

    Native or bilingual

  • English

    Fluent

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

Experience

  • Klypop
    Creation SAAS BeToBe
    RESTAURANTS AND FOOD SERVICE
    February 2026 - March 2026 (1 month)
    Paris, France
    B2B SaaS that automates order taking via WhatsApp for restaurants.

    Architecture:
    - AI Agent (LangGraph) that interacts with the user via WhatsApp.
    - Agent equipped with tools to interact with the SaaS database, create a Stripe payment link, and calculate the delivery zone.
    - Creation of the Frontend, Firebase database, Firebase authentication, Stripe payment, Railway deployment.
    LangGraph AI Agent Data visualization OAuth Python
  • CAPDIAG
    AI Developer
    REAL ESTATE
    October 2025 - October 2025
    Noisy-le-Grand, France
    Multi-agent virtual assistant for 3D tours, developed for a client and now used by over 400 people/day.
    Hybrid architecture (RAG + graph) with real-time text/audio interactions.

    Architecture:
    - Multi-agent orchestration via LangGraph.
    - Hybrid RAG: FAISS + Neo4j.
    - Optimized RAG pipeline: scoring, compression, anti-hallucination.
    - Real-time audio/text integration (GPT-4o-Realtime).
    - Robust audio queue management (listening/speaking).
    - Custom and animated React widget.
    - Web reading, document processing, image analysis.

    Automation of 60-80% of 3D tour related support.
    Langchain RAG AI Agent Chatbot OpenAI
  • MonBulletin
    AI Developer
    CONSULTING AND AUDITS
    September 2025 - September 2025
    Paris, France
    Automated payroll audit system relying on two complementary agents: a deterministic agent that recalculates all payroll figures, and a variable agent (LLM + RAG) that checks for errors according to the collective agreement.
    The pipeline allows for a reliable analysis in less than 2 minutes per payslip.

    Key points
    - OCR extraction and automatic structuring of payslip data.
    - Deterministic agent: complete recalculation of bases, rates, hours, contributions, and amounts.
    - Variable agent (LLM+RAG): verification of rules from the collective agreement.
    - Multi-agent orchestration via LangGraph for a controlled process.
    - Error detection: bonuses, surcharges, ceilings, rates, absences, overtime...
    - Specialized RAG based on legal texts + collective agreement.

    Production of a structured and explainable audit report.

    Audit time reduced from ~20 minutes to less than 2 minutes.
    Langchain LangGraph OpenAI

Reviews

5.0

Out of 1 rating

Y

Yves

dev - JYS

Several days project

-

Reviewed on 4/1/2026

Alix, Very efficient Available and full of proposals and solutions provided.

Recommendations

Be the first to recommend Alix

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

  • Certification: Fine-tuning & RL for LLMs: Intro to Post-training
    Deeplearning Ai
    2026
    Cours de la formation : - Core techniques in Fine-Tuning and RL - Evaluation of model - Data Driven Post-Training - Production Considerations
  • DAUPHINE: Mathematics and Computer Science for Decision Making and Organizations.
    MIDO Bachelor's Degree
    Mathématiques et Informatique de la Décision et des Organisations.

Skill set

Categories