Quantitative Intern

Quantitative Intern

Compensation: Unpaid

Role Overview

As a Quant Researcher Intern, you’ll work with our team to explore and model curated sports datasets, helping to uncover patterns and build predictive tools that feed directly into our proprietary betting models. This hands-on internship is ideal for someone eager to deepen their statistical and machine-learning skills in a real-world, market-driven environment. You’ll work closely under the mentorship of senior researchers, gaining exposure to advanced modeling, optimization and backtesting techniques, and end-to-end deployment practices.

Key Responsibilities

Exploratory Data Analysis & Feature Engineering

• Explore pre-processed sports datasets (e.g., advanced box-score metrics, play-by-play logs, market odds data, player-tracking metrics) to identify informative features.
• Perform EDA using statistical summaries, visualizations, and correlation analyses to guide feature selection and engineering.

Model Implementation & Backtesting

• Implement, train, and evaluate baseline predictive models (e.g., linear/logistic regression, decision trees, random forests, support vector machines).
• Use our backtesting library to optimize model parameters and validate performance and risk characteristics across historical seasons.
• Report metrics such as ROI (Return on Investment), Sharpe ratio, Value-at-Risk, and apply Monte Carlo simulation for robust estimation.

Algorithmic Experimentation

• Prototype advanced approaches under guidance (e.g., reinforcement learning, hidden Markov models, evolutionary algorithms, graph-based models).
• Tune hyperparameters using libraries like Optuna, Hyperopt, and auto-sklearn.
• Integrate large language models (LLMs) for tasks like automated feature extraction or natural-language scenario simulations.

Automation & Reproducibility

• Write clean, modular Python code (pandas, NumPy, scikit-learn, etc.) and document experiments in Jupyter notebooks.
• Commit work to GitHub, follow pull-request workflows, and maintain an internal model registry.

Collaboration & Communication

• Present findings in weekly team meetings using visualizations and key metrics.
• Contribute to internal documentation (READMEs, guides, code comments) to support transparency and reproducibility.

Technical Skills & Plus Areas

Required Foundation

• Proficient in Python (pandas, NumPy, scikit-learn, Matplotlib/Seaborn).
• Solid grasp of core statistical concepts (e.g., regression, hypothesis testing, distributions) and ML fundamentals (e.g., overfitting, cross-validation).
• Familiarity with Git version control and collaborative workflows.

Bonus Expertise

• Quantitative Finance: Signal research, alpha generation, portfolio construction, performance analysis.
• APIs & Data Integration: RESTful API experience.
• Monte Carlo Simulation: For performance and risk modeling.
• Advanced Modeling: Experience with XGBoost, LightGBM, PyTorch/TensorFlow, ARIMA, LSTM.
• Performance Optimization: Efficient code in C++ or other compiled languages.
• Cloud & Deployment: Basic AWS (S3, EC2), Docker.
• Experiment Tracking: Tools like MLflow, Weights & Biases.
• Visualization & Dashboards: Plotly, Streamlit.
• Sports Passion: Genuine interest and understanding of sports and game outcomes.

Qualifications

• Currently pursuing or recently completed a B.Sc./M.Sc. in a quantitative field (Data Science, Statistics, CS, Math, Economics, etc.).
• Open to candidates with full-time employment who can commit part-time.
• Practical experience from projects, internships, hackathons, or personal initiatives.
• Demonstrated ability to quickly learn new tools and techniques.
• Strong written and verbal communication skills.

What We Offer

• Mentorship & Growth: Learn from experienced quantitative researchers.
• Real Impact: Influence live models and strategic decisions.
• Learning Resources: Access to proprietary datasets and curated literature.
• Flexible Schedule: Adaptable hours and remote work options.
• Future Opportunities: Internship stipend and potential full-time role after graduation.