Quantitative Machine Learning Alpha Researcher

This role will focus on developing quantitative algorithmic CTA and high-frequency trading strategies using machine-learning-driven and data-driven methodologies, you will need to think about how to exploit modern machine-learning techniques on diverse financial data sets.

It's quite different from other typical machine learning jobs because our percentage-based lucrative dividends and annual bonuses are directly associated with your model's performance You will also have the opportunity to conduct independent algorithmic research.

The main programming languages are Python and Rust.

【About Us】

Quantrend Technology focuses on building financial trading strategies across a variety of asset classes and global markets.

We empower the paradigm shift from traditional quant to AI quant by using modern end-to-end deep learning models.

The difference between traditional approaches and our proprietary solution is that our models can automatically extract robust and high-quality trading signals (Alphas), but traditional hand-crafted approaches often fail to do so.

【Responsibilities】

1. Conduct quantitative research, and apply advanced modern machine learning methods to diverse data sets to build robust models for forecasting financial market risks and returns.

2. Design and implement algorithmic CTA and high-frequency trading strategies including backtesting and evaluation.

3. Research / propose/validate new effective financial market predictive features, models, and trading strategies.

4. Design and implement directional movement/volatility/risk/price impact/slippage forecasting models in CTA and high-frequency trading.

5. Deep reinforcement learning-based optimal control of trade execution, risk management, and portfolio construction.

6. Self-supervised / unsupervised learning on financial market data sets.

7. Co-work with trading system developers to deploy trading strategies in live trading environments.

【Requirements】

1. Advanced training in Mathematics, Statistics, Physics, Computer Science, Electrical Engineering, Financial Engineering, or another highly quantitative field. (Bachelor's, Master's, Ph.D. degree)

2. Strong knowledge of probability, statistics, machine learning, deep learning, time-series analysis, pattern recognition, computer vision, NLP, etc.

3. Strong programming skills in Python machine learning packages, including NumPy, pandas, scikit-learn, XGboost, Tensorflow, and Keras or PyTorch.

4. Solid experience in EDA (exploratory data analysis) using Python, familiarity with data visualization using packages including matplotlib, seaborn, etc.

5. Deep understanding of machine learning theories and algorithms, with the ability to debug ML models, tune hyperparameters, and identify and solve the root cause of model performance bottlenecks.

6. In-depth understanding of deep learning theories, network architecture design, and training/optimization techniques, with hands-on experience in the development of deep learning models.

7. Superb analytical and quantitative skills, understanding of and experience with mapping domain problems into algorithms, along with a healthy streak of creativity.

8. Entrepreneurial, highly-productive, extremely detail-oriented, with a sense of ownership of his/her work, working well both independently and within a small collaborative team.

9. Great communication and problem-solving skills.

10. Self-motivated and fast-paced learner.

【Nice to Have】

1. Bachelor's degree in financial engineering.

2. Experience in trading and in-depth knowledge of financial markets.

3. Prior experience working in a data-driven research environment.

4. Experience in training DRL (Deep Reinforcement Learning).

5. Bayesian / hierarchical probabilistic graphical modeling experience.

6. Experience in algorithmic trading.

7. Knowledge of SQL and NoSQL databases and Docker containers.

8. Experience with AWS.