Job Description

Responsibilities

• Design, build, evaluate, and maintain predictive statistical and machine learning models for player evaluation, projectable skill growth, player acquisition, tactical simulation, and performance optimization.
• Extract actionable insights from spatio-temporal tracking data to drive quantitative player evaluation.
• Conduct rigorous exploratory research using advanced quantitative techniques (e.g. Bayesian inference, spatial modeling, survival analysis, or deep learning) to uncover unexploited market inefficiencies.
• Systematically audit, backtest, and refine existing internal predictive models to ensure high accuracy and adaptability through changes in game rules or industry economics.
• Partner closely with data engineering teams to design scalable features, automated data pipelines, and production workflows for seamless model deployment.
• Translate complex probabilistic outputs and model predictions into intuitive visualizations, executive briefs, and actionable insights for front-office leaders, coaches, and scouts.

Qualifications

• Master’s or Ph.D. in Statistics, Data Science, Computer Science, Applied Mathematics, Operations Research, or equivalent practical quantitative research experience.
• Deep statistical learning knowledge and hands-on experience applying machine learning techniques, such as gradient-boosted decision trees, hierarchical/mixed-effects models, neural networks, or spatio-temporal modeling.
• Advanced programming proficiency in Python and/or R for numerical computing, data manipulation, and model development (using libraries such as scikit-learn, PyTorch, XGBoost, tidyverse, or PyMC/Stan).
• Strong command of SQL for extracting, aggregating, and joining large-scale relational datasets.
• Practical experience with software development best practices, including clean code principles, version control (Git), unit testing, and reproducible research workflows.

Nice-to-haves:

• Experience with stochastic simulation methods (e.g., Monte Carlo) or reinforcement learning for game strategy optimization and decision modeling under uncertainty.
• A portfolio of public sports analytics research, open-source sports data science projects, or competition entries evaluating athlete performance or tactical dynamics.
• Familiarity with modern MLOps workflows, containerization (Docker), and cloud infrastructure (AWS or GCP) for scaling predictive models.

Job Posting Compensation Range/Rate:

$105,000 - $115,000