Machine Learning Quantitative Researcher - Crypto Derivatives

About the role

Hytech, a management consulting firm with offices in Australia and Singapore and clients including global trading platforms and crypto exchanges, is hiring a Machine Learning Quantitative Researcher for its quantitative trading team. You will design, research, prototype and deploy machine learning models for crypto derivative market-making and systematic trading, working with quantitative researchers, traders and low-latency engineering teams to turn statistical and ML insights into production systems.

Key responsibilities

• Research, design, prototype and validate ML models for market microstructure, order book dynamics, alpha signals, price prediction, spread optimisation and execution cost modelling.
• Build backtesting, walk-forward and out-of-sample testing pipelines, and check for overfitting and regime shifts.
• Engineer features from high-frequency data such as order book snapshots, tick data, trade flows, funding rates, volume imbalance, queue dynamics and latency metrics.
• Translate trading hypotheses into ML frameworks with traders and researchers, and deploy models into low-latency market-making and execution systems.
• Develop dashboards tracking live model performance, feature drift, prediction quality and strategy PnL.
• Research market regimes, liquidity patterns, limit order behaviour and trading halts, and document findings for compliance review.
• Collaborate on stress testing and scenario simulation.

Required profile

• Master's or PhD in Computer Science, Statistics, Applied Mathematics, Physics, Quantitative Finance or a related field.
• 3+ years of hands-on experience building production ML models for systematic trading, market-making or high-frequency finance (crypto or traditional markets preferred).
• Deep understanding of market microstructure and exchange APIs; familiarity with crypto derivatives and perpetual futures is highly preferred.

Required skills

• Time-series ML: gradient boosting, neural networks, sequence models, probabilistic modelling, anomaly detection, feature engineering.
• Python (NumPy, Pandas, Scikit-learn, PyTorch / TensorFlow) and statistical foundations.
• Backtesting frameworks, performance attribution and handling overfitting.
• Nice to have: online learning, reinforcement learning, Docker, low-latency profiling, and publications in time-series forecasting or quantitative finance.