Machine Learning Quantitative Researcher – Crypto Derivatives

About Hytech

Hytech is an esteemed management consulting firm operating out of Australia and Singapore, specializing in digital transformation for the fintech and financial services sectors. Their comprehensive consulting services and dependable middle- and back-office solutions empower clients to improve operations, boost efficiency, and remain competitive in a rapidly evolving digital environment. Their clientele comprises leading global trading platforms and prominent cryptocurrency exchanges.

Role Overview

This position invites you to join the quantitative trading team to develop, research, prototype, and deploy machine learning algorithms designed specifically for crypto derivatives market-making and systematic trading strategies. You will collaborate with quantitative researchers, traders, and engineers to transform statistical and machine learning insights into live trading systems. The work encompasses applied machine learning, time-series modeling, microstructure research, and backtesting for alpha generation, improved quoting, risk management, and enhanced execution across multiple centralized crypto exchanges.

Key Responsibilities

• Conduct research and develop machine learning models focused on market microstructure, order book dynamics, signal generation, price forecasting, spread optimization, and execution cost estimation for crypto derivatives.
• Create rigorous backtesting frameworks including walk-forward and out-of-sample validation to assess model effectiveness and test for overfitting, regime shifts, and exchange-specific anomalies.
• Generate features from high-frequency market datasets such as order book snapshots, tick-level trade data, funding rates, volume imbalances, queue metrics, and latency statistics.
• Collaborate with traders and quantitative analysts to convert trading hypotheses into machine learning models and refine these based on live market feedback and strategy results.
• Implement trained machine learning models into low-latency market-making and execution platforms alongside engineering teams, balancing predictive accuracy against latency requirements.
• Develop monitoring systems to evaluate real-time model performance indicators, including concept drift, feature drift, and profitability metrics.
• Perform statistical analyses on market regimes, liquidity flows, order behaviors, and trading suspensions to adjust model assumptions and risk controls.
• Maintain thorough documentation of research processes, model designs, testing procedures, and production limitations for internal use and compliance.
• Support stress testing and scenario analyses to examine model robustness during volatile markets, exchange outages, and other disruptions.

Required Qualifications and Experience

• A Master’s or PhD in Computer Science, Applied Mathematics, Statistics, Physics, Quantitative Finance, or a closely related quantitative discipline.
• At least three years of hands-on experience developing production machine learning models for systematic trading, market-making, or high-frequency trading in crypto or traditional financial markets.
• Expertise in time-series machine learning methodologies, including gradient boosting, neural networks, sequence models, probabilistic approaches, anomaly detection, and feature engineering for high-frequency data.
• Advanced proficiency in Python and its libraries (NumPy, Pandas, Scikit-learn, PyTorch, TensorFlow), coupled with strong statistical fundamentals covering hypothesis testing, probability theory, Bayesian inference, and correlation analysis.
• A deep understanding of market microstructure including order types, limit order books, liquidity, funding mechanisms, trading halts, rate limits, and exchange API intricacies.
• Experience with backtesting systems, performance attribution, and methods to prevent overfitting in financial time series models.
• Familiarity with streaming and event-driven architectures like Kafka, Google PubSub, or Redis streams for real-time data ingestion.
• Preferred experience with low-latency trading infrastructure and capability to cooperate with engineers integrating ML models into C++ or Rust production environments.
• Strong knowledge of cryptocurrency derivatives such as perpetual futures, including understanding decentralized exchange behaviors and edge cases.
• Excellent code quality standards, experimental rigor, and effective communication skills to present complex quantitative results to non-expert stakeholders such as traders and engineering teams.

Desirable Additional Skills

• Experience with advanced machine learning concepts like online learning and reinforcement learning applied to market making and order execution.
• Practical knowledge of optimizing low-latency systems, including profiling and tuning, as well as deploying containerized applications using Docker on cloud platforms.
• Contributions to publications or open-source projects related to time-series forecasting or quantitative finance.
• Experience designing machine learning-driven risk models for real-time position monitoring.