Quantitative Trader - Sports Prediction Markets

RAVEN; Milano; In loco; EUR 120.000 - 190.000; Tempo pieno

Descrizione del lavoro

Raven in Milan is seeking a probabilistic thinker to build event models and execute market-making strategies in live crypto markets. You will translate ratings, lines, and performance data into calibrated probability distributions and set two-sided quotes accordingly.

The role requires comfort with on-call rotations, a deep grasp of statistics and machine learning, and the ability to work with fast, low-latency systems across trading regions.

Competenze

• Strong applied statistics, including Bayesian inference and hierarchical models.
• Ability to explain model validation and evidence against it.
• Experience with calibration and backtesting is a plus.

Mansioni

• Develop event models from ratings, lineups, and performance data into probability distributions.
• Set two-sided quotes on discrete outcomes with model-driven spread and size.
• Manage news, latency, and in-play updates with state-dependent repricing.
• Asses resolution risk by checking contract settlements against rules.
• Assess risk and sizing to withstand adverse market conditions.

Conoscenze

Forecasting accuracy

Probabilistic thinking

Bayesian methods

Data analysis

Communication

On-call rotation

Descrizione del lavoro

About Raven

Raven is a proprietary crypto market-making and high-frequency trading firm. We trade spot, perpetuals, and prediction markets with dedicated low-latency infrastructure across eight major trading regions.

About Raven

Raven is a proprietary crypto market-making and high-frequency trading firm. We trade spot, perpetuals, and prediction markets with dedicated low-latency infrastructure across eight major trading regions. We hire competitive individuals and natural problem solvers with a record of ranking at something hard, whether competitive programming, games, or mathematics, who treat an unfamiliar problem as a challenge rather than an obstacle. We can teach markets; we cannot teach drive. We build our own stack end to end, from connectivity and pricing through execution, monitoring, and research data.

THE ROLE

We are not a sportsbook. We do not price a margin and wait for retail flow. We quote into exchange-style markets where the counterparty may be sharper than we are, and we profitonly when our probabilities beat the price.This is the whole job. Every contract settles at zero or one, the market price is already a forecast, and your edge is being better calibrated, faster to react, or willing to make a market where no one else will.

What You'll Own

• Event models. Team and player state turned into a probability distribution, built from ratings, lineups, pace, venue and weather effects, and referee quirks. A stable of models rather than one grand unified theory, and you know exactly where each one stops working
• Quoting and market making. Two-sided prices on discrete outcomes, with spread and size that reflect how confident the model actually is, and inventory managed across outcomes that must sum to one
• News, latency, and in-play. Injuries, lineups, red cards, and delayed starts, met with state-dependent live repricing and suspension logic that withdraws quotes before adverse selection sets in
• Resolution risk. What a contract actually settles on, in the rules text and not the spirit. Real PnL, not legal boilerplate
• Risk and sizing. Position sizing that survives a bad week, correlation across events that look independent and are not, and exposure you understand before it is a problem

Who We're Looking For

• Demonstrated skill forecasting real-world events for money, supported by quantitative evidence, from a betting syndicate, professional or semi-professional betting, a research seat graded on calibration, or sportsbook trading if you can demonstrate the transition described below
• You think in probabilities and know when you are wrong. You can explain how you would validate a model, what would count as evidence against it, and which of your own models you have retired
• Strong applied statistics, including Bayesian inference, hierarchical models, time-varying team strength, and enough machine learning to know when it is the wrong tool
• Data instincts. Odds histories, lineups, injuries, and results are messy and revised after the fact, and you catch the look-ahead bias before it flatters a backtest
• If you are from a sportsbook, the transition that matters is from pricing recreational flow to competing against a market. We look for evidence you can tell the difference
• Fluent English
• Crypto and exchange microstructure are a plus
• No degree required. Experience is what matters

LOGISTICS

• Sofia (Bulgaria) or Milan (Italy), with no preference between them. Whichever city the right person is in
• In office, not remote
• Crypto trades around the clock. You will share a sane on-call rotation with the team that owns these systems