About Soufiane
English
Fluent
French
Native or bilingual
Arabic
Native or bilingual
Experience
- Servier LaboratoryLead Gen AIPHARMACEUTICALS INDUSTRYDecember 2024 - Today (1 year and 6 months)Suresnes, France
- Developed Agentic ICF system that transforms complex Clinical Study Protocol tables (spanning multiple pages, dozens of columns and rows) into concise ICF Summary Tables — reducing generation time from 1–2 days (manual) to under 5 minutes, leveraging Skills Cards architecture with scoped MCP tool restrictions.
- Developed Vision Agentic RAG system with DSPy serving a global team of medical writers; improved retrieval hit-rate@6 from 60% to 85% across thousands of indexed documents and images.
- Built custom document parser using Docling to extract tables, figures, and images from complex PDFs, RTF, and DOCX into structured Markdown and metadata; indexed into Weaviate (text) and Google Cloud Storage (thousands of images).
- •Designed comprehensive evaluation framework assessing parsing quality, retriever performance, anti-hallucination robustness, and answer generation effectiveness.
- •Re-engineered monolithic application with full streaming architecture, reducing long-running task response time from 2 minutes to ~4 seconds.
Technologies: DSPy, Agentic-RAG, Compound AI, Docling, Weaviate, Vertex AI, GCS/GCP - KPMGLead Data ScientistCONSULTING AND AUDITSApril 2024 - November 2024 (7 months)Paris, France
- Led a team of 5 Data Scientists; delivered POC in 2 months and production-ready RAG chatbot with full UI in 3 months, parsing thousands of documents (PDF, PPTX, images) for the audit department.
- •Designed compound AI architecture with DSPy optimizers: query decomposition, chain-of-thought reasoning, and multi-hop document traversal — improving answer accuracy from 70% to 94%.
- Implemented Azure Search reranking and enhanced recursive retrieval with DSPy for dynamic keyword generation; achieved ~4-second streaming response time.
- Integrated LangFuse for real-time monitoring, performance evaluation, and feedback collection.
Technologies: DSPy, Azure Search, LangFuse, Structure.io, Pytesseract, GPT - SNCF-ConnectLead Data ScientistTRANSPORTATIONNovember 2023 - March 2024 (4 months)Paris, France
- Designed and implemented QA ChatBot leveraging LlamaIndex RAG and LangChain, covering dozens of FAQ topics with sub-50ms retrieval latency, eliminating manual searches for support agents.
- Employed auto-retriever composition on Vespa.ai for enhanced passage retrieval; implemented LangFuse monitoring for performance evaluation and continuous FAQ enrichment.
Technologies: LangChain, LlamaIndex, DSPy, Amazon Bedrock, Vespa.ai, OpenAI, LangFuse
Recommendations
Be the first to recommend Soufiane
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Docteur en Mathématiques AppliquéesUniversité Cadi Ayyad2016• Approximation discrètes des Equations différentielles Stochastiques Rétrogrades • Contributions à l'étude des processus de Lévy et des processus fractionnaires via le calcul de Malliavin et applications en statistiques • Le théorème central limite en probabilité et statistiques pour les mouvements Browniens sous-fractionnaires et bi-fractionnaires • Problème de portefeuille avec contraints stochastiques • Problème de switching avec contrainte
- Master recherche (MASEF): Mathématiques Appliquées à la Finance à l’Economie & l’Assurance -Université Paris DAUPHINE – ENSAE2008Master recherche (MASEF): Mathématiques Appliquées à la Finance à l’Economie & l’Assurance -
Certifications
- Google Cloud Platform Big Data and Machine Learning FundamentalsCoursera2019