Machine Learning for Market Structure Alpha

Prioritising a scientific and data-driven approach across the full research process and chain of production, the work is uniquely positioned in that it involves the full research and production lifecycle: idea generation, data acquisition, data curation and integration, systematic alpha signal generation / strategy design, hypothesis testing, model validation, backtesting, risk management, and buy-side strategy execution.

Key responsibilities include, but not limited to:

• Deployment of market structure research and methodologies, including identifying repeatable short-to medium-term market inefficiencies on mid-frequency horizon across US equities markets.
• Data science proficiency, including collection and preprocessing of large datasets.
• Transform data and extract predictive signals, including and across order flow, volume profile, liquidity, volatility regimes, strength of demand tests, etc.
• Develop and implement AI models / machine learning algorithms to support primary alpha (and generate new alphas).
• Design, test, and deploy systematic alpha signals and develop intraday strategies on low time frames.
• Research and develop algorithmic trade execution.
• Maintain rigours of data-driven and scientific approach, supported by key technicals.
• Trade execution.
• Portfolio management.

To achieve key objectives, the role includes

• Advanced mathematical applications as well as active problem solving.
• Python-based data analysis (Pandas etc.), including advanced statistical analysis and modelling.
• AL model building / machine learning engineering and deployment, primarily utilising Pytorch along with various methodological approaches and experimentation.
• Utilisation of common algorithms, including linear Regression, decision trees, and hierarchical clustering, as well as novel algorithm development and design.