Job Description

MLE — Systematic Trading

Trading & Financial Systems · Full-time

Systematic Trading · Quantitative Finance · ML / AI Agents · Live Markets

ABOUT THE ROLE

You will own end-to-end delivery of trading systems — from design and backtest through to live deployment — working across our brokerage's full stack of algorithmic trading, risk management, and market infrastructure. Alongside experienced quants and treasury, you will operate on real capital in live markets across multiple asset classes.

This role suits a self-starter with 3–5 years of production experience who is comfortable taking full ownership of projects, making architectural decisions, and iterating quickly in a fast-moving trading environment.

WHAT YOU WILL BE DOING

Design and implement live trading systems covering flow analysis, hedging algorithms, position management, and real-time risk controls
Own the full development lifecycle of quantitative infrastructure: strategy research, backtesting, simulation, and production deployment
Develop pricing models, hedging systems, and portfolio optimization algorithms grounded in mathematical finance
Build and maintain real-time market data pipelines and trading API integrations across exchanges, brokers, and liquidity providers
Create production monitoring and analytics dashboards to track trading performance, system health, and market conditions
Apply ML and AI agent techniques — signal generation, anomaly detection, pattern recognition, autonomous strategy workflows — where they create measurable edge
Drive reliability and scalability improvements across existing trading infrastructure

WHAT YOU NEED TO BE SUCCESSFUL

Core requirements:

Bachelor's or Master's degree in Computer Science, Financial Engineering, Mathematics, Physics, Statistics, or a related quantitative field
3–5 years of professional experience owning quantitative systems in production — backtesting frameworks, execution algorithms, or risk management systems — at a brokerage, fintech, or trading firm
Expert-level Python with deep command of numpy, pandas, scipy, asyncio and numba; proven track record of performance-tuning production-grade numerical code
Solid grasp of financial markets: trading mechanics, order types, market microstructure, and exchange API integration (e.g. Binance, OKX, Bybit, or similar)
Hands-on experience with real-time data streaming: WebSocket, message queues (Kafka or equivalent), and low-latency system design
Strong mathematical foundation with ability to implement quantitative models and statistical methods from research papers
Working knowledge of P&L calculation, position sizing, portfolio risk metrics, and core derivatives pricing concepts
Comfortable with agentic coding workflows (e.g. Claude Code, Cursor, or similar) and experienced in reviewing, validating, and shipping AI-generated code into production — including testing, code review discipline, and knowing when not to trust the model
Self-motivated with ability to take full ownership from design through production deployment with minimal direction

Bonus if you also have:

Understanding of derivatives products (options, futures, perpetuals) and margin trading mechanics — margin requirements, liquidation risk, funding rates
Familiarity with ML frameworks (scikit-learn, XGBoost, or similar) and their application to financial prediction problems; experience building or orchestrating AI agents in a production context is a strong plus
Experience with brokerage operations, cryptocurrency trading systems, arbitrage strategies, or cross-exchange workflows
Knowledge of market-making, liquidity provision, or systematic trading strategies in live environments
Contributions to quantitative finance open-source projects or published research

WHAT SUCCESS LOOKS LIKE

In your first 90 days, you will own at least one live system improvement deployed to production — whether a latency reduction, a new hedging signal, an improved risk control, or a data pipeline upgrade. Within six months, you will be the primary technical owner of one or more core trading systems, with full visibility into their performance and a roadmap for future development.