Fabien Pierret

ML Engineer / Data Engineer | Remote Specialist

About

Technical professional specializing in Apple Silicon Architecture, Data Engineering, and Machine Learning. Proven expertise in building scalable ML pipelines, processing Tera-bytes of data, and optimizing systems for real-time performance.

Highly productive in remote, asynchronous environments with exceptional written communication skills (bilingual French/English).

Core Competencies

AI/ML & Data Engineering

  • Machine Learning (Meta-Labeling)
  • Data Engineering (Polars, Parquet, Dollar Bars)
  • Feature Engineering (FracDiff, TDA, Microstructure)
  • Scientific Validation (CPCV, DSR)
  • Massive Data Processing (Tera-bytes)

Architecture & Systems

  • Apple Silicon (M4 Max)
  • CoreML, MLX
  • Local-First Architecture
  • Blockchain (Solana)
  • Computer Vision (OCR, YOLO)

Languages & Tools

  • Python (Advanced)
  • Polars, Pandas, NumPy
  • XGBoost, CatBoost
  • Git, GitHub
  • Documentation & Technical Writing

Key Projects

Renaissance V3+

Complete ML trading pipeline with advanced data engineering, feature engineering (FracDiff, TDA), Meta-Labeling, and scientific validation (CPCV, DSR). Processes Tera-bytes of crypto data.

Python Polars XGBoost CatBoost Parquet
View on GitHub →

Poker GTO-RT

Real-time poker analysis system with computer vision and GTO solver. Optimized for < 400ms latency on Apple Silicon.

Python CoreML YOLO OCR GTO
View on GitHub →

Titan DeFi

Blockchain scanner and flash-loan simulator for Solana. Processes 302k accounts with Borsh decoding.

Python Solana Jito Blockchain
View on GitHub →

GlassBox

SEC EDGAR data ingestion system. Processes 580+ companies with automated parsing pipeline.

Python Web Scraping Data Parsing JSON
View on GitHub →

SQL ETL Pipeline

Production-ready SQL ETL pipeline with data validation, transformation, and loading. Demonstrates SQL proficiency and ETL best practices.

Python SQL ETL SQLAlchemy Pandas
View on GitHub →

Work Style

Remote-First : 100% remote, asynchronous communication

Text-Based : Excellent written communication (English/French)

Self-Directed : Autonomous, proactive, results-oriented

Documentation : Strong technical documentation skills