Quantitative Researcher (Machine Learning)

Quantitative Researcher (Machine Learning)

We are seeking a talented Quantitative Researcher to join our competitive global quantitative trading team at Geneva Trading. In this role, you’ll research, develop, and deploy automated intraday and mid-frequency trading strategies using machine learning models and advanced quantitative methods. You’ll work with large datasets, applying statistical techniques to drive real-time trading decisions.
As part of a lean, skilled team, you will contribute across the entire pipeline, from data preprocessing to model deployment, ensuring the integration of research and real-time execution. This hands-on role combines quantitative research with software engineering, requiring strong coding abilities and the application of CI/CD, DevOps, and MLOps principles.
Key Responsibilities:
Design and execute research experiments to develop innovative models and strategies, evaluating results rigorously.
Develop production-ready code for live trading integration, collaborating with developers.
Enhance research and trading infrastructure through machine learning methods, including data preprocessing, feature selection, model training, and backtesting.
Monitor live trading strategies for performance issues such as covariate shift.
Integrate external libraries into production code following best engineering practices.
Optimize model training and backtesting using parallel, distributed, and cloud computing.
Explore opportunities for strategy expansion across global futures products.
Stay current with industry advancements through research, competitions, and online communities.
Required Qualifications:
Academic Background : Master’s or PhD in a STEM field (e.g., Machine Learning, Computer Science, Physics).
Experience : 2+ years of applied machine learning experience in a commercial or academic setting, or 2+ years in quantitative research or development in trading.
Skills :
Strong understanding of multivariate statistics, time-series analysis, machine learning, and optimization.
Strong programming skills in Python, including libraries like NumPy, Pandas, and Scikit-learn.
Familiarity with Q/KDB and Git.
Strong mathematical ability in linear algebra and calculus.

#J-18808-Ljbffr