Summary: Moreton Capital Partners seeks a Quant Researcher Intern to design, test, and refine predictive models for live trading portfolios in commodity futures. Highlights: 1. Research, prototype, and validate systematic trading signals using advanced ML. 2. Develop portfolio construction and optimization techniques. 3. Deep exposure to commodity markets and ML research workflows. ### **Quant Researcher Intern – Systematic Commodities Hedge Fund** Moreton Capital Partners is seeking a talented Quant Researcher Intern to help build the next generation of alpha signals in commodity futures. Our research is grounded in advanced machine learning, robust testing frameworks, and a deep understanding of global commodity markets. This role is central to our mission: you’ll take ownership of designing, testing, and refining predictive models that directly feed into live trading portfolios. ### **Key Responsibilities** * Research, prototype, and validate systematic trading signals across commodities using advanced ML methods. * Design and implement rigorous backtests with realistic frictions, walk\-forward validation, and robust statistical tests. * Engineer and evaluate novel features from prices, fundamentals, positioning, options data, and alternative datasets (e.g., satellite, weather and global commodity cash pricing). * Blend multiple alpha forecasts into meta\-models and portfolio signals, leveraging ensemble and Bayesian methods. * Develop portfolio construction and optimization techniques and analysis tools to be able to enhance performance and track effects on portfolio execution. * Collaborate with developers to transition research into production\-ready strategies. Monitor live performance, attribution, and model drift, ensuring continual improvement of the alpha library. **Requirements** * Bachelors degree in either Statistics, Economics, Computer Science. * Strong background in machine learning and statistical modelling (tree\-based models, regularisation, time\-series ML). * Proficiency in Python (pandas, NumPy, scikit\-learn, XGboost, PyTorch/TensorFlow). * Understanding of time\-series forecasting, cross\-validation techniques, and avoiding look\-ahead bias. * Academic experience in research and proven ability to translate academic work to production code. * Prior exposure to systematic trading or financial modelling. * Ability to design experiments, interpret results, and iterate quickly in a research environment. Bonus points for: * Knowledge of commodities (agriculture, energy, metals) or macro markets. * Experience with feature engineering on non\-traditional datasets (options positioning, weather, satellite). * Experience collaborating in version control environments. * Familiarity with portfolio optimisation, risk parity, or Bayesian model averaging. * Publications, Kaggle competitions, or research track record demonstrating applied ML excellence. **Benefits** * Research\-first culture: We value deep thinking, novel approaches, and systematic rigor. * Close collaboration across a global team. * Learning curve: Deep exposure to commodity markets, ML research workflows, and institutional\-grade trading systems.