Senior Soccer Sports Betting ML / Quantitative Modeler

Summary We are building a serious pregame soccer betting prediction system, starting with Major League Soccer (MLS) and eventually expanding into major soccer leagues and competitions worldwide. We are looking for a Senior Soccer Sports Betting ML / Quantitative Modeler. However, there is one important distinction: We are NOT primarily looking for a generic machine-learning engineer. We want someone who is first and foremost extremely knowledgeable about soccer and sports betting, and who also has the technical ability to translate that knowledge into a high-quality quantitative prediction system. The ideal candidate is the type of person who has followed soccer for years, understands the sport deeply, follows players, teams, managers, leagues, competitions, transfers, tactical styles, historical results, and current developments — and also understands how sportsbooks and betting markets actually work. You should be genuinely comfortable discussing soccer across: MLS Premier League La Liga Serie A Bundesliga Ligue 1 Champions League Europa League Copa Libertadores World Cups Euros Copa América International soccer Major domestic leagues and cups You should know the history of the sport, major clubs and players, how teams and leagues differ stylistically, how competition formats work, how squads evolve, and how factors that may not appear cleanly in a spreadsheet can influence a match. For this initial project, strong MLS knowledge is particularly important, because MLS will be our first league. At the same time, you must understand sports betting extremely well — sportsbooks, odds, probabilities, vig, line movement, market efficiency, closing prices, expected value, Asian handicaps, totals, 1X2 markets, and the practical difficulty of beating modern betting markets. Finally, you need the technical capability to actually build, audit, and improve the prediction system using Python, machine learning, statistical models, AI, historical data, and modern modeling techniques. The type of person we want We are particularly interested in someone who combines three areas of expertise: 1. Deep soccer knowledge You should be a genuine soccer expert / fanatic. We want someone who understands the sport far beyond basic statistics. You should understand things such as: Teams and historical team strength Major players, past and present Managers and tactical systems Formations and tactical matchups Player roles Squad depth Transfers Injuries and suspensions Starting lineups Rotation International call-ups Club and international competitions Promotion/relegation systems Domestic league differences Major tournaments Soccer history World Cups Champions League League champions across major countries MLS structure and history MLS roster peculiarities Travel and scheduling in MLS Home-field effects Player importance beyond simple goals/assists How team quality changes when particular players are missing Coaching changes Tactical changes Motivation and competition context where statistically defensible Differences between regular season, knockout, cup, and international matches We don't want someone who learned what xG means six months ago because they saw it in a dataset. We want someone who already understands soccer deeply and can use data and modeling to formalize that knowledge. 2. Strong sports betting knowledge You should also understand soccer betting at a serious level. We expect familiarity with: Sportsbooks Betting exchanges Pinnacle-style markets Sharp vs recreational books 1X2 markets Moneyline Asian handicaps European handicaps Draw No Bet Double Chance Totals Team totals Both Teams to Score Alternate lines Closing lines Opening lines Market movement Implied probability Vig / juice No-vig probabilities Expected value Closing-line value ROI Hold Liquidity Limits Stale prices Line shopping Market efficiency You should understand why: being able to predict soccer reasonably well is not the same thing as being able to beat a sportsbook. Modern soccer markets are competitive. We are specifically looking for somebody who understands the difficulties involved in building a profitable pregame betting model today. 3. Strong quantitative / ML / technical ability You should then have the technical skills required to convert soccer and betting knowledge into a production-quality prediction system. Relevant experience may include: Python LightGBM XGBoost CatBoost Scikit-learn Statistical modeling Bayesian modeling Machine learning Probability models Forecasting Feature engineering Model calibration Monte Carlo simulation Poisson models Dixon-Coles models Bivariate Poisson ELO-style rating systems Player ratings Team ratings Neural networks where justified Ensemble models SHAP Backtesting Data pipelines Time-aware validation We care about the methodology more than using any particular model. A complicated neural network that produces bad probabilities is much less useful to us than a well-designed simpler model that is correctly calibrated and robust. What we are building Our initial objective is a pregame MLS prediction model. The initial markets are: MLS 1X2 / moneyline MLS spreads / Asian handicaps MLS game totals Potential future markets include: Both Teams to Score Draw No Bet Double Chance Team totals Alternate handicaps Alternate totals First-half markets Player props Eventually, we want the architecture to expand beyond MLS into other soccer leagues. What the prediction system should produce We expect the system to eventually produce: Home-win probability Draw probability Away-win probability Expected goals for the home team Expected goals for the away team Expected total goals Expected goal differential Asian handicap probabilities Over/under probabilities BTTS probability Confidence / uncertainty indicators Betting edge compared with available sportsbook prices Expected value Clear explanations of why the model prefers a particular side or market Probabilities must be properly calibrated. If the model repeatedly predicts outcomes at 60%, approximately 60% of comparable predictions should occur over a sufficiently large sample. Soccer knowledge must influence the architecture We don't want a model that simply downloads a CSV and trains LightGBM on team statistics. You should be able to think critically about how soccer actually works. For example: Team strength How should we determine the real underlying strength of a team? Possible information includes: xG for xG against Non-penalty xG Shots Shot quality Big chances Field tilt Possession Progressive actions Pressing Set pieces Opponent-adjusted performance Home performance Away performance Schedule strength Tactical style But we need someone who understands when these metrics are actually meaningful and when they are misleading. Player and lineup strength Soccer is highly sensitive to personnel. A team's historical rating alone may not accurately represent the team playing tonight. We want to properly model: Starting XI Projected starting XI Confirmed lineups Injuries Suspensions International absences Transfers Rotation Player quality Expected minutes Position Replacement quality Bench strength Formation Tactical changes Key attacker absences Key defender absences Goalkeeper changes Losing Lionel Messi, for example, cannot simply be represented as: injured_players = 1 The system needs a way to estimate the actual effect of missing players on team strength and expected goals. MLS expertise is particularly valuable Our first production league will be MLS. Therefore, we are particularly interested in someone who understands MLS-specific characteristics such as: Eastern vs Western Conference travel Long-distance travel Time-zone differences Extreme climate differences Altitude Artificial turf MLS roster construction Designated Players International player availability CONCACAF Champions Cup Leagues Cup U.S. Open Cup Canadian Championship International windows Schedule congestion Cross-country road trips Squad rotation MLS playoff structure Differences between MLS and European leagues Someone who already follows MLS closely will have a major advantage. Expected goals and score distributions We expect expected goals and scoring distributions to be an important part of the architecture. The system may estimate: Home xG / expected goals Away xG / expected goals Total expected goals Expected goal difference We then need to determine the best method of translating those predictions into market probabilities. Possible approaches include: Poisson Dixon-Coles Bivariate Poisson Negative binomial Bayesian models Monte Carlo simulation Machine-learning-based goal models Hybrid ML + statistical models We are not committed to one approach. We want the modeler to explain why a methodology makes sense and understand its limitations. Draw modeling Draws are one of the reasons soccer prediction is different from many American sports. We need someone who understands how to correctly model: Home win Draw Away win rather than treating soccer like a binary classification problem. The predicted score distribution and 1X2 probabilities should be internally coherent. If the goal model implies one distribution but the 1X2 classifier produces contradictory probabilities, we want someone capable of identifying and resolving that problem. Sportsbook and market layer The model cannot exist independently from the betting market. We need a framework that: Converts sportsbook odds correctly Removes vig correctly Handles three-way 1X2 markets Handles two-way markets Handles Asian handicap settlement Calculates true expected value Compares model probabilities to market probabilities Monitors line movement Measures closing-line value Accounts for market uncertainty Defines minimum edge thresholds Knows when NOT to bet We are not interested in a model that produces hundreds of theoretical "+EV bets" because of incorrect probability math. Realistic historical backtesting This is extremely important. A model can look amazing historically and still be worthless if its backtest is unrealistic. Every historical prediction should use only information that would actually have been available at that point in time. For example: If the model claims that a bet was placed four hours before kickoff, it cannot use a starting lineup announced one hour before kickoff. Historical backtests may therefore require timestamped information for: Sportsbook odds Opening prices Closing prices Line movement Injuries Suspensions Projected lineups Confirmed lineups Transfers Coaching changes International call-ups Rest Travel Weather Other competitions Match data Player data We want someone who is naturally suspicious of a model reporting extraordinary historical ROI. Problems we expect you to identify Examples include: Data leakage Future information appearing in historical predictions Closing prices accidentally entering model features Bad train/test splits Random instead of chronological validation Unrealistic odds timestamps Incorrect vig removal Incorrect 1X2 probability normalization Incorrect Asian handicap calculations Broken EV calculations Incorrect ensemble weighting Probability blending that mathematically doesn't make sense Poor calibration Overconfident probabilities Double-counting correlated features Overweighting recent results Using goals instead of underlying expected performance Treating finishing variance as sustainable skill Overvaluing tiny samples Ignoring lineup changes Ignoring player quality Ignoring goalkeeper changes Ignoring schedule congestion Ignoring travel Ignoring competition context Unrealistic ROI Betting edges that disappear against closing prices Model evaluation Accuracy alone is NOT enough. We care about: Log loss Multiclass log loss Brier score Calibration Reliability curves Ranked Probability Score Expected-goal prediction error Closing-line value Expected value Realized ROI Betting volume Performance by edge bucket Performance by confidence Performance by odds range Performance by market type Performance by prediction timestamp A model can have good winner accuracy and still be unusable for betting if its probabilities are poorly calibrated. Understanding the difficulty of beating soccer markets This is something we specifically want applicants to address. We do NOT assume that because we have machine learning, large datasets, and powerful computers we can automatically beat sportsbooks. We want someone who understands why modern soccer betting markets are difficult. That might include issues such as: Highly efficient prices Information rapidly entering the market Strong closing lines Data quality Historical data leakage Lineup information Player valuation Market reaction to injuries/news Limited true independent signal Feature redundancy Small sample sizes Concept drift Different league dynamics Bookmaker limits Execution differences Odds availability Stale historical prices Overfitting Selection bias Multiple-testing bias We expect the person hired to be realistic about these challenges. We are not looking for someone promising guaranteed profit or unrealistic ROI. Required experience Soccer domain knowledge — critical Deep knowledge of professional soccer Strong understanding of players, teams, leagues, managers, and competitions Strong understanding of soccer history Knowledge of World Cups and major international tournaments Knowledge of Champions League and major European leagues Knowledge of major domestic competitions Strong understanding of formations and tactics Strong understanding of player roles and lineup strength Ability to reason about soccer beyond what is directly visible in a dataset Betting knowledge — critical Strong understanding of sportsbooks Strong understanding of soccer betting 1X2 markets Asian handicaps Totals Implied probabilities Vig / no-vig Expected value Market movement Closing-line value Market efficiency Realistic backtesting Technical knowledge — required Strong Python Machine learning Probability modeling Statistical modeling LightGBM / XGBoost / comparable models Calibration Feature engineering Time-aware validation Backtesting Data analysis Model diagnostics Highly preferred Direct MLS modeling experience Direct MLS betting experience Strong personal knowledge of MLS Professional soccer analytics experience Previous soccer prediction systems Previous profitable or market-competitive soccer betting models xG modeling Poisson / Dixon-Coles experience Player valuation models Starting-XI strength models Soccer ELO / rating systems Opta StatsBomb Wyscout Sportradar Stats Perform Betting exchange data Pinnacle data Historical odds databases Asian-market experience What success looks like By the end of the initial engagement we want: A defensible MLS prediction architecture Trustworthy home/draw/away probabilities Sensible expected-goal projections Sensible handicap probabilities Sensible totals probabilities Proper probability calibration Realistic uncertainty estimates Good modeling of player availability Good modeling of starting-lineup strength Proper consideration of MLS-specific factors Realistic timestamp-aware backtesting Correct sportsbook/EV calculations Clear model explanations Identification of leakage or weak assumptions A framework capable of expanding into other soccer leagues Engagement details Sport: Soccer / Football Initial league: MLS Future expansion: Global soccer leagues and competitions Initial markets: 1X2, Asian handicap/spread, totals Type: Model design, model audit, quantitative research, implementation Engagement: Initial project with strong potential for ongoing work Hours: Flexible Level: Senior / Expert only IMPORTANT — What to include in your cover letter Please do not send us a generic AI/ML proposal. We specifically want to evaluate your soccer knowledge, betting knowledge, and practical understanding of this problem. Please answer the following: 1. Tell us about your relationship with soccer. How long have you followed the sport? Which leagues and competitions do you follow most closely? Do you follow MLS? We want to understand whether soccer is genuinely one of your areas of expertise. 2. Demonstrate your soccer knowledge. Briefly tell us about: Leagues you understand particularly well Competitions you follow Teams / players / eras you know particularly well Your knowledge of MLS You don't need to write an essay, but we want to distinguish genuine soccer experts from candidates who only work with soccer datasets. 3. Tell us about your sports betting experience. What markets have you modeled or bet? Explain your experience with: Sportsbooks Odds Vig No-vig probability EV Closing-line value Asian handicaps 1X2 Totals 4. Tell us about soccer models you have built before. Please include: Leagues Markets Data Modeling approach Validation Results Whether you tracked CLV 5. How would you architect an MLS pregame prediction model? At a high level, explain how you would connect: Team strength Player strength Starting lineups xG Expected goals Score distributions 1X2 Asian handicaps Totals Sportsbook prices 6. What makes building a profitable soccer betting model difficult in 2026? This is one of the most important questions. Tell us the things you would be most cautious about when building this system. We especially want to hear about the practical problems, limitations, biases, market-efficiency issues, and backtesting traps you would actively watch for. 7. What soccer-specific mistakes do you commonly see data scientists make? We want examples where having strong soccer domain knowledge changes how you would interpret the data or design the model. 8. How would you value a missing player? For example, how would you model the effect of a star striker, central midfielder, center back, or starting goalkeeper being unavailable? 9. How would you distinguish true improvement/decline from short-term form? For example, a team may have won four games consecutively despite poor underlying xG. How would your system treat that? 10. How would you model draws? Explain how you would ensure that home/draw/away probabilities are coherent with expected goals and the predicted score distribution. 11. How would you audit suspicious historical performance? If an existing model showed unusually high historical ROI, what would you investigate first? 12. What information must be timestamped? What data would you require to reconstruct a realistic historical prediction without accidentally using information from the future? 13. What technical stack and modeling approaches would you use? Mention the languages, frameworks, statistical models, ML models, and data architecture you would be comfortable using. Final note We would rather hire: an exceptional soccer + betting expert who is a very strong modeler than: an exceptional generic ML engineer who knows very little about soccer or betting. The domain knowledge matters enormously for this role. If soccer is something you genuinely follow, study, analyze, and understand at a high level — and you also have the quantitative and technical skills to build a serious betting model — we would like to speak with you. Recommended skills Soccer MLS Sports Betting Soccer Analytics Machine Learning Python Quantitative Research Predictive Modeling Probability Statistics Artificial Intelligence Expected Goals Sports Analytics Model Calibration LightGBM XGBoost Bayesian Statistics Poisson Models Feature Engineering Forecasting