Build models that meet real markets
We're a small, research-first team building mid- and high-frequency trading strategies with deep learning, statistical machine learning and mathematical models. Everyone who joins now shapes the core of what we build.
What working here is like
We care about rigour more than titles, and results on unseen data more than results on slides.
Research over hype
An idea counts when it survives walk-forward testing, realistic costs and live shadow trading. Not before.
Own the whole problem
You'll take ideas from raw data to a live strategy, working across research, engineering and risk.
Work at two speeds
Our problems span millisecond order book dynamics and multi-day statistical arbitrage. You'll learn both.
Open roles
Click a role to see the full details.
Quant Researcher
What you'll do
- Design, test and refine trading signals across mid- and high-frequency horizons
- Build deep learning and machine learning models on market and order book data
- Run rigorous validation: walk-forward tests, purged cross-validation and cost modelling
- Take strategies from research into live shadow trading, working closely with engineering
What you'll bring
- A strong foundation in probability, statistics, linear algebra and time series
- Fluent Python and the scientific stack: NumPy, pandas or Polars, scikit-learn
- Hands-on experience training machine learning or deep learning models
- A habit of distrusting results that look too good
Bonus points
- PyTorch and modern sequence architectures such as transformers
- Research publications, or a master's or PhD in a quantitative field
- Kaggle or trading competition results
- Knowledge of market microstructure
Quant Developer
What you'll do
- Build and run data pipelines for market and order book data
- Develop our backtesting and market simulation engine
- Build the low-latency execution layer for our high-frequency stack
- Create tooling that makes research faster and fully reproducible
What you'll bring
- Strong Python, plus C++ or Rust
- Solid Linux, networking and cloud (AWS) fundamentals
- Experience with large datasets using tools like Polars, Arrow and Parquet
- Clean, tested, well-documented code
Bonus points
- Low-latency systems experience, including kernel bypass or FPGAs
- Exchange APIs and the FIX protocol
- Distributed computing and GPU workloads
Don't see your role?
If you're exceptional at mathematics, machine learning or systems engineering and want to work on trading problems, write to us anyway. Tell us what you'd want to work on and why.
How hiring works
Short, technical and respectful of your time.
Apply
Email your CV and links to your work. We reply to every application.
Intro call
A 30-minute conversation about your background and what you want to build.
Technical problem
A realistic research or engineering problem, close to what you'd work on here.
Final conversation
A deeper discussion of your solution with the founder, and next steps.