Trading systems engineering, proven on our own capital.
Most consultants sell advice they've never had to live with. We build, deploy, and operate algorithmic trading systems with our own money on the line — then bring that same engineering to solo quants, emerging funds, and fintech teams who need institutional-grade infrastructure without the institutional headcount.
Built for the underserved middle of quant finance.
Tier-one funds have armies of engineers. Retail traders have indicator scripts. Everyone in between — the people actually building businesses on systematic trading — has been left to improvise. That's who we serve.
Solo quants & independent traders
You have an edge in research but your execution stack is held together with cron jobs and hope. We turn your strategy into a monitored, fault-tolerant production system you can trust overnight.
Emerging funds & prop teams
You need backtest validation, data pipelines, and execution infrastructure that survives due diligence — without a £250k engineering hire. Fixed-scope builds with full knowledge transfer.
Fintech & trading-tool startups
You're building a product on top of market data or broker APIs and need someone who has actually operated against Alpaca, exchange feeds, and cloud deployment in anger — not just read the docs.
The four failure modes that kill systematic trading.
We've hit every one of these running our own systems. The fixes below aren't theory — they're what we deploy for ourselves.
Your backtest is lying to you
Look-ahead leakage, survivorship bias, and overfitting inflate paper Sharpe until live capital exposes the truth. We validate strategies with purged walk-forward testing and deflated performance metrics before a single real order is placed.
- Purged & embargoed cross-validation
- Deflated Sharpe and overfitting probability
- Regime-segmented walk-forward analysis
Your data pipeline manufactures false signals
As-of joins done wrong, unadjusted corporate actions, and silent feed gaps create alpha that never existed. We build point-in-time-correct pipelines with drift detection and full lineage.
- Point-in-time feature stores
- Automated data-quality and drift monitors
- Corporate-action and calendar correctness
Your system fails exactly when it matters
Volatility spikes are when fragile systems die — and when the P&L is decided. We engineer for the bad day: health checks, kill-switches, position reconciliation, and automated recovery on cloud infrastructure.
- Deployment on GCP with monitored rollouts
- Kill-switches and drawdown circuit breakers
- Broker-state reconciliation and alerting
Your risk is an afterthought
Position sizing bolted on at the end is how accounts blow up. We design regime-aware sizing, exposure limits, and portfolio construction into the system from day one — because ours depend on it.
- Regime detection and adaptive sizing
- Portfolio-level exposure and correlation limits
- Pre-trade risk checks in the execution path
We publish what we run. No invented case studies.
These systems trade every market day on Google Cloud against live market data. They are our research platform, our proving ground, and the honest answer to "have you actually done this?"
Balanced Portfolio Engine
Regime-aware multi-asset portfolio system with adaptive position sizing and drawdown circuit breakers. Our most conservative book.
Read the engineering notes → LiveFrontier Optimizer
Efficient-frontier portfolio optimization fused with an NLP news-sentiment pipeline that tilts allocations as the information environment shifts.
Read the engineering notes → LiveVolume Predictor
Machine-learning intraday volume forecasting — the execution-timing signal that underpins our other systems and the first candidate for our public API.
Read the engineering notes →Why teams choose us over the alternatives.
| Full-time quant hire | Generalist consultancy | 1.21 Initiative | |
|---|---|---|---|
| Cost structure | £150k–£250k/yr, ongoing | Open-ended billable hours | Fixed-scope engagements with defined deliverables |
| Skin in the game | Salary either way | None — incentivised by hours | We run the same methods on our own capital |
| Who does the work | Depends who you can attract | Partners sell, juniors deliver | The person you talk to is the person who builds |
| Speed | 3–6 months to hire, more to ramp | Weeks of discovery before code | AI-accelerated delivery — working software in weeks |
| What you keep | Knowledge walks when they do | Dependency by design | Full code ownership, docs, and handover — zero lock-in |
Book a free 30-minute working session.
Bring your strategy, your stack, or your idea. You'll get a straight technical assessment of where it's fragile and what we'd do about it — whether or not you hire us. Same-day response, no sales deck.
Direct technical response from the engineer who does the work.