Athletic background
Before AI, there was squash.
A decade in a sport that rewards reading a match faster than your opponent can play it — and the habits of mind it left behind.
- World junior ranking
- Top 9
- World Junior Team Championships
- First place — Egypt
- International
- Represented Egypt
- Collegiate
- Trinity College
The career
I grew up in Egypt, which is to squash roughly what Brazil is to football. The standard at every level is absurd, and the only way through it is to get better than the people you train with.
I became a three-time Egyptian junior national champion and won the British Junior Open U13 title, then competed among the leading juniors in the world — reaching the top 9 in the world junior rankings and representing Egypt internationally, including at the World Junior Team Championships, where the Egyptian team finished first in the world.
I later moved to the United States and competed for Trinity College, one of the most successful programmes in collegiate squash, where I earned College Squash Association All-American honours, First Team All-NESCAC recognition, and won the Molloy Division at the CSA Individual Championships. I went on to compete professionally.
Squash at that level is less physical chess than people assume and more an information game played at speed. You are simultaneously executing, reading an opponent, and updating a model of them that has to be right within the next three shots. The players who win consistently aren't necessarily the fastest — they're the ones whose read is more accurate more often.
Record
Selected results
- Top 9 in the world junior rankings—
- World Junior Team Championships — Egypt finished first—
- Three-time Egyptian junior national champion—
- British Junior Open U13 champion—
- College Squash Association All-American—
- First Team All-NESCAC—
- Molloy Division winner, CSA Individual Championships—
- Competed professionally—
What it taught
Habits that transferred
Not motivation — method. These are the specific things elite sport trains that turned out to be directly useful in engineering.
Thinking in patterns
You stop watching individual shots and start watching what recurs. That is, functionally, the same instinct that makes someone useful at looking at data.
Iteration with fast feedback
Form a hypothesis, test it in a rally, get an honest answer immediately. Sport is a feedback loop tight enough that you learn to stop defending ideas that aren't working.
Marginal improvement
Nothing in a training block feels significant on its own. The improvement is real anyway. It made me comfortable with engineering work that only pays off cumulatively.
Decisions under pressure
At 9–9 you decide with incomplete information and no time. It's a good calibration for shipping decisions, where waiting for certainty is usually the more expensive option.
Measurable performance
You cannot argue with a scoreline or a fitness test. That expectation — that a claim should be measurable — is the thing I most directly carried into building AI systems.
Preparation as an edge
The work that decides a match mostly happened before it. The same is true of production systems: the evaluation you built beforehand is what saves you later.
Squash → AI
From reading matches to teaching machines to read them
Competitive squash taught me to analyse a match in a way a scoreboard cannot. The score tells you who is winning. It tells you nothing about why. The useful information is in the patterns underneath it.
- Where does a player recover to, and how fast?
- What happens to their shot selection under pressure?
- Which positions on court create attacking opportunities?
- What patterns repeatedly lead to errors?
- How does shot choice change with court position?
- What does an opponent do at 9–9?
As a player, I answered those questions by watching — my own matches, my opponents', the same rally a dozen times looking for the tell. It was slow, subjective, and limited to the footage I had the patience to sit through.
Years later I recognised the same questions in a different form. Where does a player recover to is a tracking problem. What happens under pressure is a temporal pattern problem. What leads to errors is a sequence-modelling problem. Every question a coach asks about a match turns out to be a computer vision, machine learning or data problem underneath.
Core Sports AI came out of that observation. Not that AI should replace the intelligence coaches and elite athletes build over years — it can't — but that a system able to watch thousands of movements, shots, positions and rallies could surface the patterns that a person would need a season of tape study to notice.
Contact
Building something at the intersection of AI and the real world?
I'm glad to hear from engineers, founders, researchers, coaches and athletes — and from anyone working on AI systems that have to be right rather than merely impressive.