Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Sofiane Derraz, a GenAI Architect & Data Scientist who designs end-to-end data solutions that blend predictive analytics with generative AI. I translate complex AI concepts into reliable production systems that drive measurable business impact across fraud detection, analytics, and enterprise platforms. I build end-to-end GenAI pipelines, LLM architectures, and MLOps infrastructures, aligning data science rigor with engineering discipline to deliver scalable AI at production scale and accelerate innovation.…Hi, I’m Sofiane Derraz, a GenAI Architect & Data Scientist who designs end-to-end data solutions that blend predictive analytics with generative AI. I translate complex AI concepts into reliable production systems that drive measurable business impact across fraud detection, analytics, and enterprise platforms. I build end-to-end GenAI pipelines, LLM architectures, and MLOps infrastructures, aligning data science rigor with engineering discipline to deliver scalable AI at production scale and accelerate innovation.

Sofiane Derraz

Data Scientist, AI Engineer, Architect, +2





Hi, I’m Sofiane Derraz, a GenAI Architect & Data Scientist who designs end-to-end data solutions that blend predictive analytics with generative AI. I translate complex AI concepts into reliable production systems that drive measurable business impact across fraud detection, analytics, and enterprise platforms. I build end-to-end GenAI pipelines, LLM architectures, and MLOps infrastructures, aligning data science rigor with engineering discipline to deliver scalable AI at production scale and accelerate innovation.…Hi, I’m Sofiane Derraz, a GenAI Architect & Data Scientist who designs end-to-end data solutions that blend predictive analytics with generative AI. I translate complex AI concepts into reliable production systems that drive measurable business impact across fraud detection, analytics, and enterprise platforms. I build end-to-end GenAI pipelines, LLM architectures, and MLOps infrastructures, aligning data science rigor with engineering discipline to deliver scalable AI at production scale and accelerate innovation.

Available to hire

Hi, I’m Sofiane Derraz, a GenAI Architect & Data Scientist who designs end-to-end data solutions that blend predictive analytics with generative AI. I translate complex AI concepts into reliable production systems that drive measurable business impact across fraud detection, analytics, and enterprise platforms.

I build end-to-end GenAI pipelines, LLM architectures, and MLOps infrastructures, aligning data science rigor with engineering discipline to deliver scalable AI at production scale and accelerate innovation.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

French

Fluent

English

Advanced

Russian

Intermediate

Work Experience

GenAI Architect at Digifab.fr

January 1, 2024 - Present

Architected and deployed end-to-end LLM pipelines handling daily requests; optimized inference latency through model quantization and batching. Designed multi-model orchestration supporting GPT, Claude, and open-source LLMs; implemented intelligent routing reducing API costs by 35%. Built proprietary Retrieval-Augmented Generation (RAG) system leveraging vector databases (PostgreSQL/pgvector) and semantic search; improved content relevance scores by 28% with prompt engineering. Analyzed content usage patterns and user behavior; identified optimization opportunities increasing feature adoption by 22%. Implemented containerized microservices (Docker + Kubernetes) for seamless model serving and auto-scaling; established ML monitoring (drift detection, latency tracking) and automated retraining pipelines using MLflow. Reduced cloud storage costs by 30% through intelligent data versioning and lifecycle management. Built CI/CD pipelines for model deployment with sub-minute deployment cycles

Artificial Intelligence Consultant at Paris je t'aime

February 1, 2023 - Present

Delivered predictive analytics and forecasting for ticket stock optimization (18% improvement in inventory turnover), tourist flow forecasting with 92% accuracy enabling dynamic pricing strategies, and customer demand modeling to optimize resource allocation. Developed NLP-driven automation bot, automating 80% of routine tasks; implemented sentiment analysis to inform product roadmap. Built real-time dashboards and competitive intelligence tools to support strategic decisions in a tourism-focused context; migrated deployment to Azure with CI/CD, reducing deployment times to minutes.

Artificial Intelligence Consultant at Headn

November 1, 2022 - January 31, 2023

Led NLP & text classification initiatives: built end-to-end pipeline for extracting signals from 100k+ reviews; trained fine-tuned BERT model achieving high F1 on multi-label classification; engineered 40+ signals from unstructured text to enable data-driven career guidance for learners. Built robust data collection and ETL pipelines for 500k+ reviews with high data quality; delivered incremental data updates and scalable processing.

Artificial Intelligence Consultant at L'ADN

January 1, 2022 - October 31, 2022

Implemented predictive lead scoring and B2B analytics; deployed ensemble models improving purchase-intent prediction and sales ranking. Built multi-source data fusion pipeline across 20+ sources with 98% data deduplication. Developed SHAP-based interpretability framework and interactive dashboards to improve ML adoption among sales teams.

Artificial Intelligence Consultant at FranceVerif

January 1, 2021 - December 31, 2021

Fought internet fraud with production fraud-detection model (XGBoost + deep ensembles) achieving 97% precision and 94% recall. Implemented real-time streaming pipeline with sub-100ms latency, preventing multi-million-dollar annual losses. Engineered 150+ behavioral/ transactional features and implemented anomaly detection to expand coverage; built interpretability dashboards for investigators.

Data Scientist at W'ant

June 1, 2020 - August 31, 2020

Advanced tourism analytics: scraped 50k+ platform reviews; built NLP sentiment model (87% accuracy) and topic modeling to identify drivers of satisfaction. Automated data collection and cleaning pipelines, delivering near real-time insights via an interactive Superset dashboard; supported regional tourism strategies with data-driven recommendations.

Digital Data Analyst at FADSA - Fonds d'Aide au Développement du Sport en Afrique

January 1, 2020 - February 29, 2020

Analytics framework for e-commerce channels: multi-touch attribution, A/B testing, and optimization of landing pages. Improved conversion rate from 2.1% to 3.7% and average order value by 18%. Built dashboards for ROI by channel and customer acquisition costs; enabled data-driven budget allocation.

Data Analyst - Business Intelligence at ISOPROM

July 1, 2019 - August 31, 2019

Assessed 8 BI tools and defined a decision-support architecture for multiple business domains. Built ETL pipelines to a data warehouse with 95% data freshness, implemented data quality checks, and trained teams on dimensional modeling to accelerate report production.