Job Description
Company Description Trade W is a leading multi-asset trading platform with over seven years of industry experience, providing global users with secure, convenient, and efficient access to the financial markets. We offer CFD trading across a wide range of asset classes — including forex, cryptocurrencies, stocks, indices, metals, and commodities — through our intuitive app and web platform.
Launched in 2018 as the flagship brand of Tradewill Global LLC, Trade W was built on a customer-first philosophy and a vision to make trading success more accessible. Today, we continue to grow as a trusted platform, committed to empowering traders worldwide with equal opportunities for success.
About the Role We are seeking a highly capable Risk Data Scientist to join our Dubai team and drive the development of large-scale risk analytics and real-time monitoring systems. You will work across high-frequency, derivatives, and multi-asset trading data to detect anomalies, optimize risk parameters, and support trading, routing, and market-making strategies. This role works closely with global risk, trading, and engineering teams to improve system robustness, accuracy, and profitability.
What You’ll Do:1. Data Engineering & Pipelines Build and maintain real-time and historical data pipelines for orders, trades, positions, and funds. Develop ETL workflows, ensuring unified metric and dimension definitions across systems. Own data consistency, quality, and latency for mission-critical risk processes.2. Real-Time Risk Monitoring & Control Develop highly visual risk dashboards by platform/product/account level. Implement risk order detection, anomaly detection, automated alerts, and circuit-breaker logic. Drive automated risk parameter tuning and safeguard mechanisms.3. Factor & Indicator Research Extract and validate risk and behaviour factors from historical data (e.g., markout, VPIN, volatility structure, flow imbalance). Integrate factors into risk models, market-making engines, routing policies, and evaluation frameworks.4. User Segmentation & Profiling Build classification models for retail vs. professional vs. arbitrage vs. HFT user types. Create risk grading models to improve strategy selection and routing optimization.5. PnL Attribution & Monitoring Build daily pipelines for PnL attribution covering fees, spread, funding, basis, and slippage. Run P&L anomaly detection and generate automated notifications.
Core Skill: Strong SQL/Spark/Hive/Click House; data modeling, materialized views, performance tuning. BI tools: Fine BI, Power BI, Tableau. Understanding of: exposure, leverage, Greeks, hedge deviation, failure/latency rates, VaR/ES, TCA, plus factor backtesting metrics (IR, Sharpe, Max Drawdown). Scikit-learn: classification/regression, anomaly detection, feature engineering, drift monitoring. Familiarity with PyTorch / Tensor Flow. Spark/Flink, Kafka/Redpanda, Airflow/Dagster. Data quality frameworks such as Great Expectations. Proficient in Python/Java, with strong engineering and code quality practices.
Preferred Qualifications Bachelor’s degree or above in Computer Science, Data Science, Financial Engineering, or related fields. Knowledge of risk control, anomaly detection, clustering, time-series analysis. Experience in derivatives, leveraged trading, FX/CFD, or multi-asset risk management. Strong risk sense with ability to connect models to business decisions. Excellent cross-functional communication with global teams (risk, trading, engineering).