We are looking for a Machine Learning/AI Engineer to build and optimize predictive models for the “Magnificent 7” stocks (NVDA, AAPL, META, TSLA, GOOG, MSFT, and AMZN), using techniques like time-series analysis, sentiment modeling, and advanced feature engineering.
As a Machine Learning/AI Engineer, you’ll design, implement, and maintain a range of advanced AI/ML models aimed at boosting trading performance. Using up to a decade’s worth of historical market data — collected daily, every 4 hours, or hourly — you’ll ensure robust, data-driven insights that power our core strategies.
Requirements
- At least 5 years of experience in Machine Learning or AI-related roles with a focus on financial data modeling, quantitative analysis, or algorithmic trading systems
- Proficiency in Python, with hands-on experience using libraries such as TensorFlow, PyTorch, scikit-learn, and XGBoost
- Familiarity with big data frameworks (e.g., Spark, Dask) and cloud platforms like AWS or GCP
- Proven track record of developing and deploying trading models or financial strategies
- Strong experience in time-series forecasting, financial data analysis, and feature engineering for stock market data, including technical indicators and sentiment analysis
- Expertise in hyperparameter tuning techniques, model optimization, and performance enhancement
- Solid foundation in statistics, probability, and optimization methods, with knowledge of risk management metrics such as Sharpe Ratio, Alpha, and Beta for portfolio optimization
- At least an Upper-Intermediate level of English
WILL BE A PLUS
- Experience in proprietary trading, hedge funds, or asset management firms
- Knowledge of trading platforms such as Interactive Brokers, Alpaca, or similar systems
- Knowledge of options pricing, derivatives, or quantitative trading strategies
- Familiarity with alternative data sources, including news sentiment, social media trends, and other non-traditional datasets for market analysis
- Experience with transformer models (both language and visual)
- Hands-on experience with backtesting tools like Zipline or Backtrader
- Familiarity with Docker, Kubernetes, and CI/CD pipelines for scalable model deployment
Personal Profile
- Strong critical thinking and problem-solving skills, with the ability to assess and challenge model assumptions
- Excellent communication skills for presenting complex concepts
- Ability to work both independently and collaboratively in fast-paced, dynamic environments
Responsibilities
- Collect, clean, and preprocess historical financial data, extracting meaningful features such as moving averages, RSI, and volatility indicators to enhance model performance
- Design and train predictive models (e.g., LSTM, XGBoost, Random Forests) with rigorous backtesting, hyperparameter tuning, and evaluation using metrics such as Sharpe Ratio, Sortino Ratio, and Maximum Drawdown
- Deploy models in production environments, monitor performance, address data drift through retraining, and collaborate with teams to integrate insights into trading systems while maintaining thorough documentation
