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

Anass Smali

AI Engineer

€150/day
Paris, FR
0-2 years

Average response time: 1 hour

Freelancer profile translated to English.
Back to original language

About Anass

  • French

    Native or bilingual

  • English

    Native or bilingual

  • German

    Basic

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

Experience

  • SEW USOCOME
    Data & AI Engineering Intern
    January 2024 - June 2024 (5 months)
    Strasbourg, France
    • Design of a complete image processing and OCR pipeline for extracting industrial information from high-resolution images.
    • Training of CNN models (TensorFlow / Keras) for text zone detection and use of EasyOCR for character recognition.
    • Fine-tuning of LLMs (GPT, Mistral, Llama) on extracted text to improve understanding and semantic structuring of data.
    • Automatic generation of structured outputs (JSON) and integration into a MongoDB database for analysis and visualization.
  • SEW USOCOME
    AI Engineer
    June 2025 - September 2025 (3 months)
    • Development of an intelligent assistant based on a RAG (Retrieval-Augmented Generation) architecture to automate access to technical documentation. Implementation of a complete data processing pipeline (ingestion, parsing, PDF segmentation) via LangChain and PyPDF2, with embedding generation and indexing in Milvus for efficient semantic search.
    • Orchestration of multiple LLMs (GPT-4, Claude 3, LLaMA 3) with optimization of prompting strategies to improve the relevance and contextualization of responses. Design of an intuitive user interface using Streamlit.
    • Deployment of the solution with containerization (Docker) and implementation of performance evaluation via RAGAS (relevance, faithfulness, coherence of responses).

    Results: 50% reduction in document search time and significant improvement in response quality.
  • SEW EURODRIVE
    Data & AI Engineering Intern
    June 2025 - August 2025 (2 months)
    • Design of a predictive maintenance solution for industrial machinery in an Industry 4.0 context.
    • Preprocessing and analysis of time series data with InfluxDB and Python (cleaning, imputation, segmentation).
    • Development and evaluation of unsupervised anomaly detection models: ConvLSTM-VAE, Isolation Forest, Transformer Informer.
    • Deployment of a complete application integrating a FastAPI backend and a Streamlit dashboard for visualization and export.
    • Results: early detection of 70% of failures and a 20% reduction in unplanned downtime.

Recommendations

Be the first to recommend Anass

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

  • Engineering Degree in Data Science & AI (SDIA)
    Télécom Physique Strasbourg
    2026
    Diplôme d'ingénieur en Informatique et Réseaux
  • Master in Data Science and Complex Systems
    Université de Strasbourg
    2026
    Master en Sciences des Données et Systèmes Complexes

Categories