[Closed] Machine Learning/AI Engineer for Algorithmic Trading

Role Overview
As a Machine Learning/AI Engineer, you will work on developing, training, and deploying advanced AI/ML models such as LSTMs, XGBoost, and other algorithms tailored to optimize trading strategies. The ultimate goal is to achieve a Sharpe ratio exceeding 3 on these stocks, leveraging up to 10 years of historical market data on daily, 4-hour, or hourly timeframes.

Key Responsibilities

Data Processing & Management:
— Collect, clean, and preprocess up to 10 years of historical market data for NVDA, AAPL, META, TSLA, GOOG, MSFT, and AMZN.
— Engineer features such as moving averages, RSI, volume trends, volatility indicators, and others to enhance model inputs.

Model Development & Training:
— Design, train, and evaluate models including LSTM, XGBoost, Random Forests, and ensemble methods.
— Optimize models for risk-adjusted returns, ensuring a Sharpe ratio > 3 is achievable.
— Experiment with alternative architectures, including transformer models, for timeseries prediction.

Hyperparameter Tuning:
— Conduct extensive hyperparameter tuning to enhance model performance using grid search, Bayesian optimization, or other methods.

Evaluation & Validation:
— Backtest models rigorously with historical data and validate forward-looking performance.
— Assess model performance using statistical metrics such as Sharpe ratio, Sortino ratio, and maximum drawdown.

Deployment & Monitoring:
— Deploy models in a production environment with minimal latency.
— Monitor real-time predictions, retrain models periodically, and address data drift.

Collaboration & Reporting:
— Work closely with the quant team and software engineers to integrate models into trading systems.
— Document research, experiments, and results clearly and concisely. Requirements:

Technical Skills:
— Proficiency in Python with expertise in libraries such as TensorFlow, PyTorch, scikit-learn, and XGBoost.
— Strong experience with time-series forecasting and financial data modeling.
— Knowledge of feature engineering for stock market data (e.g., technical indicators, sentiment analysis).
— Experience with backtesting frameworks and tools like Zipline or Backtrader.
— Familiarity with big data technologies (e.g., Spark, Dask) and cloud platforms like AWS or GCP.
— Hands-on experience with hyperparameter tuning techniques and model optimization.

Quantitative Skills:
— Strong foundation in statistics, probability, and optimization.
— Familiarity with risk management and portfolio optimization metrics like Sharpe ratio, beta, and alpha.

Experience:
— Minimum 3-5 years of experience in ML/AI roles, preferably in finance or algorithmic trading.
— Proven experience in building and deploying trading models or strategies for financial markets.

Soft Skills:
— Problem-solving mindset and ability to think critically about model assumptions.
— Strong communication skills to explain complex models to non-technical stakeholders.
— Ability to work independently and collaboratively in a fast-paced environment.

Preferred Qualifications:
— Master’s or Ph.D. in Computer Science, Data Science, Mathematics, or related fields.
— Previous experience in proprietary trading, hedge funds, or asset management firms.
— Knowledge of trading platforms like Interactive Brokers or Alpaca.
— Familiarity with alternative data sources (e.g., news sentiment, social media trends).