Senior ML Quant Engineer

Paragon Alpha - Hedge Fund Talent Business; Paris; On-site; EUR 120,000 - 180,000; Full time

Job summary

Paragon is seeking an elite Senior Quant Engineer to elevate their research and production infrastructure for systematic trading. You will build robust data ingestion, feature generation, backtesting, and experiment tracking pipelines, with a focus on tick and orderbook data and market microstructure.

Responsibilities include turning strategies into production systems, validating data and models, and applying ML to predictive signals while controlling for overfitting and leakage.

Responsibilities

• Build and maintain research infrastructure for data ingestion, feature generation, backtesting, and experiment tracking.
• Focus on tick data, orderbook data and market microstructure.
• Turn strategies into production systems with signal logic, portfolio construction, and execution workflows.
• Validate data and models for errors, look‑ahead bias, overfitting, and realistic trading costs.
• Apply machine learning to build and evaluate predictive signals with controls for overfitting and leakage.
• Monitor live strategies, track performance, risk, system health, and unexpected behavior.
• Improve reliability and speed by optimizing code and making pipelines reproducible and robust.

Skills

Python

Machine Learning

Data Ingestion

Backtesting

Tools

FastAPI

Pandas

SQL

Airflow

AWS

Job description

Paragon are representing a world class systematic trading house, working with an MF equity team.

We have been mandated to find an elite Senior Quant Engineer to take the build to the next level.

Focus:

• Build and maintain research infrastructure for data ingestion, feature generation, backtesting, and experiment tracking.
• Specific focus on tick data, orderbook data and market microstructure
• Turn strategies into production systems, implementing signal logic, portfolio construction, and execution workflows.
• Validate data and models, checking for errors, look-ahead bias, overfitting, and realistic trading costs.
• Apply machine learning to build and evaluate predictive signals, with careful controls for overfitting and data leakage.
• Monitor live strategies, tracking performance, risk, system health, and unexpected behavior.
• Improve reliability and speed, optimizing code and making trading and research pipelines reproducible and robust.

Stack: Python, Machine Learning, FastAPI, Pandas, SQL, Airflow, AWS