Guide · overview
Quant interview questions, by role
43 problems · 9 min read · updated 2026-09-07
"Quant interview" covers three quite different exams. A trading interview at Optiver or SIG is mental math, expected value and market-making games under a clock. A research interview at Two Sigma or D. E. Shaw is probability theory, statistics, stochastic processes and a coding round. A risk or portfolio interview at a bank or asset manager is VaR, Sharpe, duration and the pricing identities behind them.
The questions below are grouped so you can see the overlap and the differences. Every role gets the probability core; after that the weighting diverges sharply. Pick your lane, then use the role tracks on LeetQuant to drill in order.
The probability core every role gets
Conditional probability, expectation of stopping times, Bayes with real numbers, and the birthday-style counting arguments. If you can only prepare one section, prepare this one — it is in every first round.
A fair coin is tossed twice. Given that at least one toss is heads, what is the probability that both are heads?
Answer: 1/3 · Worked solution →
What is the expected number of flips of a fair coin until the first head appears?
Answer: 2 · Worked solution →
Two fair six-sided dice are rolled. What is the expected value of the larger of the two (ties count as that value)?
Answer: 4.472 · Worked solution →
A disease affects 1% of a population. A test is 99% sensitive (true-positive) and has a 1% false-positive rate. Given a positive test, what is the probability the person actually has the disease?
Answer: 0.5 · Worked solution →
What is the smallest number of people in a room for which the probability that at least two share a birthday exceeds 50%? (Ignore leap years.)
Answer: 23 · Worked solution →
You roll a fair six-sided die repeatedly. What is the expected number of rolls until you have seen all six faces?
Answer: 14.7 · Worked solution →
Three doors: one hides a car, two hide goats. You pick a door; the host (who knows) opens a different door revealing a goat, then offers you the switch. What is your probability of winning the car if you switch?
Answer: 2/3 · Worked solution →
Market making and games (trading)
Quote a fair value and a spread, then defend it when the interviewer starts trading against you. Kelly sizing, adverse selection and optimal-stopping games are the modern trading interview — often the whole second round.
An interviewer asks you to make a market on the sum of two fair six-sided dice. Before you quote a bid and an ask, you need the fair value. What is it?
Answer: 7 · Worked solution →
You roll a fair die and are paid its face value in dollars, but you may re-roll up to two times, keeping only the final roll. Playing optimally, what is this game worth?
Answer: 4.67 · Worked solution →
A binary asset settles at 100 or 0, each with probability 1/2. Of the traders who arrive, 20% are informed (they know the outcome and trade in its direction) and 80% are noise traders who buy or sell with probability 1/2 each. A single trader arrives and buys from you at your ask. To break even in expectation against this flow, what is the lowest ask you can quote?
Answer: 60 · Worked solution →
A repeatable bet wins with probability 40%. A win pays 2-to-1 (win 1 staked); a loss costs the stake. What fraction of your bankroll should you stake per bet to maximise long-run growth (the Kelly fraction), in percent?
Answer: 10 · Worked solution →
Everyone in a large group simultaneously picks a number from 0 to 100. The winner is whoever is closest to two-thirds of the group average. If every player is perfectly rational and knows everyone else is too, what number does game theory say everyone picks?
Answer: 0 · Worked solution →
Cards from a shuffled standard 52-card deck are revealed one at a time. Your running total gains 1 for every black card. You may stop whenever you like and collect the running total (you may also stop immediately at $0). Playing optimally, what is this game worth?
Answer: 2.62 · Worked solution →
Stochastic processes and pricing (research, derivatives)
Random walks, Brownian motion, martingales and the no-arbitrage identities that follow from them. Put-call parity and risk-neutral pricing are asked at banks and prop shops alike; Itô and hitting-time questions are research-desk territory.
You start with 1 on a fair coin each round, stopping when you reach 100. What is the probability you reach $100 before going broke?
Answer: 0.3 · Worked solution →
What is the expected number of fair-coin flips to get two heads in a row (HH)?
Answer: 6 · Worked solution →
For a standard Brownian motion , what is ?
Answer: 3 · Worked solution →
European call and put share strike K = 100 on a non-dividend stock at S = 100, with rate r = 0 and maturity T = 1. The call trades at 8. What is the fair price of the put?
Answer: 8 · Worked solution →
A stock at 100 will move to 120 or 80 in one period. With interest rate r = 0, what is the risk-neutral probability of an up move?
Answer: 0.5 · Worked solution →
Roughly what is the delta of an at-the-money European call on a non-dividend stock with short time to expiry?
Answer: 0.5 · Worked solution →
A stock follows geometric Brownian motion with given. What is ?
Statistics and inference (research)
Estimators, variance of the sample mean, regression identities, and the paradoxes that test whether you understand conditioning. Systematic funds ask these to see if you can reason about a backtest honestly.
State the Central Limit Theorem, and give the standard deviation of the sample mean of n i.i.d. draws with variance σ².
In a simple linear regression of Y on X, the slope is Cov(X, Y)/Var(X). If Cov(X, Y) = 4 and Var(X) = 8, what is the slope?
Answer: 0.5 · Worked solution →
Tanks are serial-numbered 1, 2, …, N. You capture 4 tanks and the largest serial number observed is 60. Using the standard minimum-variance unbiased estimator, what is your estimate of N?
Answer: 74 · Worked solution →
X and Y are independent random variables with the same variance. What is the correlation between X and X + Y?
Answer: 0.707 · Worked solution →
You average 100 iid observations, each with variance 25. What is the variance of the sample mean?
Answer: 0.25 · Worked solution →
A drug shows a higher recovery rate than placebo among men, and a higher recovery rate than placebo among women — yet a lower recovery rate overall when the groups are pooled. Explain precisely how this can happen, and give a concrete numeric example.
Risk and portfolio (risk, asset management)
Sharpe, VaR and its scaling, minimum-variance weights, Kelly, drawdown. These are computational rather than clever — the interviewer wants the formula, the number, and one sentence on what it hides.
A portfolio returns 12% with 20% volatility; the risk-free rate is 2%. What is its Sharpe ratio?
Answer: 0.5 · Worked solution →
A portfolio’s daily return is Normal with mean 0 and standard deviation 2%. What is the 1-day 95% Value at Risk, expressed as a percent of portfolio value? (e.g. 3.29)
Answer: 3.29 · Worked solution →
Assuming i.i.d. normal daily returns, by what factor do you scale a 1-day VaR to get a 10-day VaR? (Round to 2 decimals.)
Answer: 3.16 · Worked solution →
Two uncorrelated assets have volatilities 10% and 20%. In the minimum-variance portfolio, what weight goes to the 10% (lower-vol) asset?
Answer: 0.8 · Worked solution →
You can repeatedly make an even-money bet (win or lose the amount staked) that you win with probability 60%. What fraction of your bankroll should you bet each time to maximize long-run growth?
Answer: 0.2 · Worked solution →
A fund’s value series is 100, 120, 90, 110, 80, 130. What is the maximum drawdown, as a percent? (Round to 2 decimals.)
Answer: 33.33 · Worked solution →
Coding (research, and increasingly trading)
LeetCode-medium with a quantitative twist: sampling, streaming statistics, dynamic programming. Research interviews always have a coding round; trading firms now add one for quant-trader roles.
You throw N uniform random points into the unit square and count the fraction that land inside the quarter unit circle. To estimate π, what should you multiply that fraction by?
Answer: 4 · Worked solution →
How to approach these in the interview
Prepare for the role, not for "quant". A trader who drills Itô calculus and a researcher who drills mental math are both wasting the week before the interview. The role tracks on LeetQuant (Trader, Researcher, Risk) exist to fix exactly this.
Fluency beats coverage. Interviewers change numbers and add a twist. The candidate who can re-derive the expected number of flips for two heads in a row under a biased coin is safer than one who memorised 2/p + 1/p².
Talk while you compute. Every firm on this list grades communication. "I will condition on the first flip" is worth more than a silent correct answer.
Bring the code round up to the rest. Research candidates lose offers on a mediocre coding round more often than on probability. Thirty LeetCode-mediums in the sampling / DP / heap families cover most of it.
Frequently asked
What is the difference between a quant trader and a quant researcher interview?
Trading interviews (Optiver, SIG, IMC, Jane Street trading track) emphasise speed: mental math, expected value, market-making games, brain teasers, often with a clock. Research interviews (Two Sigma, D. E. Shaw, Citadel research) emphasise depth: probability theory, statistics, stochastic processes, and a serious coding round. Both share the probability core.
How long should I prepare for a quant interview?
Four to eight weeks of daily practice is typical for a strong STEM background. The 30-day plan on LeetQuant covers the whole bank at about six problems a day; the 60-day plan adds spaced review so early topics do not decay by interview week.
Do quant interviews still ask brain teasers?
Trading firms do, in early rounds. Research firms have largely replaced them with probability and statistics questions that test the same reasoning with more structure.
Which topics are asked most often?
Across firms: conditional probability and expected value first, then market-making and betting games at trading firms, then statistics and stochastic processes at research firms. Options Greeks and put-call parity appear anywhere derivatives are traded.
Practise these with answer checking and spaced review
All 188 problems, full worked solutions, and a review queue that brings each one back before you forget it. Free.
Get started freeRelated guides