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

Loubna M.

Data Scientist / LLM ENGINEER

€850/day
Paris, FR
3-7 years

Average response time: 1 hour

About Loubna

Ingénieure en data science et intelligence artificielle (Mines x Télécom Paris), 5 ans d’expérience en data science et data engineering (Bouygues, Allianz, Total). Aujourd’hui spécialisée en IA générative (LLM, RAG, LangChain, Llama, Falcon) et en pipelines data à grande échelle (Spark, SQL, AWS). J’accompagne mes clients du cadrage à la mise en production, avec une double expertise :
• Applications LLM : recherche augmentée (RAG), chatbots métier, embeddings sur mesure
• Pipelines & DataOps : Spark, Databricks, ETL, AWS, SQL
• MLOps : Docker, FastAPI, CI/CD, monitoring
• Data storytelling : transformer les analyses en décisions concrètes

Objectif : livrer des solutions robustes et impactantes, adaptées à vos enjeux métiers.
  • French

    Native or bilingual

  • English

    Native or bilingual

  • German

    Conversational

  • Arabic

    Basic

Remote only
Primarily works remotely

Experience

  • Euler Hermes
    data scientist freelance
    BANKING AND INSURANCE
    March 2024 - Today (2 years and 2 months)
  • Auto entrepreneur
    LLM engineer
    January 2024 - Today (2 years and 5 months)
    • Built custom Retrieval-Augmented Generation (RAG) pipelines combining vector databases (Faiss, Pinecone), Langchain orchestration, and LLMs (LLaMA, GPT, Falcon) for knowledge-intensive tasks (e.g. support automation, document Q&A, expert systems).
    • Fine-tuned open-source models (LLaMA, Mistral) on domain-specific corpora using PEFT (LoRA) and supervised fine-tuning.
    • Integrated embedding generation workflows (OpenAI, HuggingFace) for scalable vectorization and semantic search.
    • Deployed inference services with FastAPI, Docker, and GPU orchestration on AWS/GCP.
    • Ensured latency/quality tradeoffs with prompt engineering, reranking, and hybrid retrieval.
    • Contributed to architectural decisions: RAG vs Finetuning, latency vs accuracy, model hosting strategies.
    • Collaborated with cross-functional teams (product, infra, business) to translate abstract ideas into working prototypes.

    Technologies: Python, Langchain, Faiss, OpenAI, HuggingFace, LLaMA, Mistral, FastAPI, Docker, AWS, GCP.
  • Bouygues Telecom
    Data scientist
    TELECOMMUNICATIONS
    March 2022 - Today (4 years and 3 months)

Recommendations

Be the first to recommend Loubna

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

  • Ingénieur
    Telecom Paris
    2022
    Computer Science
  • Ingenieur
    Mines Saint Étienne
    2021

Skill set (32)

Categories