AI/ML Quant Researcher — Live Sports Modeling & Signal Research

We are looking for a strong AI/ML Quant Researcher, Applied Mathematician, Statistical Modeler, Machine Learning Researcher, PhD student, postdoc, or exceptionally talented early-career quantitative researcher to help with an applied sports modeling and signal research project. The primary focus is NBA live-game modeling, using historical pricing data, play-by-play data, and game-context data. We are especially interested in candidates who understand, or can quickly learn, how player impact, rotations, substitutions, lineups, fatigue, foul trouble, injuries, rest, and game-state dynamics affect live win probability. A strong mathematical foundation is important. We are especially interested in candidates with depth in probability, statistics, Bayesian modeling, stochastic processes, optimization, time-series analysis, simulation, machine learning, or quantitative research. Experience with European football / soccer analytics is also a plus, as similar research methods may eventually be applied to football match-event data. This is not a dashboard or reporting role. We are looking for someone who can reason deeply, design rigorous tests, work with noisy real-world data, and separate true predictive signal from statistical noise. What You’ll Work On Formulate and test research hypotheses Identify structural shifts in live-game probability Detect change points or nonlinear game-state effects Model player, lineup, fatigue, foul trouble, rest, injury, and substitution effects Build Bayesian, probabilistic, statistical, or ML-based models Run historical simulations and backtests Evaluate robustness, calibration, overfitting risk, and false positives Help convert promising research into usable modeling logic Produce clean notebooks and concise research summaries Required Skills Strong mathematical foundation Probability and statistics Bayesian or probabilistic modeling Machine learning Time-series or sequential modeling Regression, classification, or hierarchical models Structural break / change-point detection Simulation or Monte Carlo methods Backtesting and model validation Python or R SQL Ability to work with noisy real-world datasets Nice to Have NBA play-by-play or possession-level data Player impact modeling Lineup and rotation analysis Win probability or game prediction models Odds, pricing, or market-style data European football / soccer analytics Football match-event data Neural networks or deep learning LLMs or AI agents for research acceleration Quantitative finance or trading research experience Deliverables Initial deliverables may include: Research notebooks Hypothesis testing and signal validation Statistical / ML model prototypes Backtesting simulations Written summaries of findings Recommendations on which signals are worth further development Project Structure We are open to starting with a smaller paid research project or trial assignment, then expanding if there is a strong fit. This could become an ongoing part-time or contract-to-hire role. To Apply Please include: A short overview of your quantitative / ML background Relevant work in mathematics, statistics, probability, ML, Bayesian modeling, quantitative finance, sports analytics, or backtesting Links to GitHub, papers, notebooks, Kaggle, models, or prior research work Any experience with Python, SQL, time-series data, backtesting, or noisy real-world datasets A brief note on how you would approach finding true signal versus noise in live NBA data