Quantitative Trader

JOB DESCRIPTION: Quant Machine Learning Engineer

Position Title:

Quant Machine Learning Engineer

Department:

Algo Trading / Quantitative Research & Engineering

Location:

Hybrid / On-Site

Role Type:

Full-time • Core Technical Position • High-Impact

⸻

ROLE OVERVIEW

The Quant Machine Learning Engineer is responsible for designing, building, and deploying AI-driven trading systems, including predictive models, optimizers, reinforcement learning agents, and execution intelligence modules.

The engineer integrates market microstructure knowledge with ML systems to enhance strategy accuracy, reduce risk, and improve execution quality.

This is a mission-critical role that powers the core trading engines of the firm.

⸻

KEY RESPONSIBILITIES

1. Strategy Intelligence & Signal Research

• Build ML-based predictive models (LSTM, Transformers, CNNs, Gradient Boosting, etc.) for short-term price forecasting.

• Create regime-detection systems using clustering / HMM / volatility modeling.

• Engineer deep-feature datasets from tick data, orderflow, and alternative data sources.

2. Model Development & Optimization

• Design reinforcement learning agents for execution, position sizing, and dynamic SL/TP.

• Implement Bayesian optimization, Optuna, Hyperopt for parameter tuning.

• Build ensemble models to improve robustness.

3. AI-Augmented Trading Infrastructure

• Develop AI-based Optimizers for SL/TSL/Targets/filters.

• Build numerical-pattern recognition engines (“number algos”).

• Integrate models with MetaBots for real-time monitoring and risk control.

4. Data Engineering & Pipelines

• Build automated pipelines for tick data ingestion, preprocessing, cleaning.

• Implement nightly retraining pipelines (Airflow/Prefect).

• Manage data versioning via MLflow / DVC.

5. Real-Time Deployment

• Convert research models into low-latency production code.

• Integrate signals into execution engines (Flattrade API, MT5, Oanda, Binance, etc.).

• Monitor latency, slippage, and model drift.

6. Portfolio-Level Intelligence

• Develop predictive risk models (volatility clusters, correlation matrices).

• Build capital allocation engines based on model confidence.

• Prevent cluster-risk across strategies and markets.

7. Continuous Improvement

• Track model performance and conduct A/B tests.

• Maintain documentation, dashboards, and audit-ready logs.

• Collaborate with quant researchers & automation engineers.

⸻

REQUIRED SKILLS & COMPETENCIES

Technical

• Strong Python (NumPy, Pandas, Scikit-Learn, TensorFlow, PyTorch).

• Knowledge of ML algorithms: supervised, unsupervised, deep learning, RL.

• Understanding of trading systems, indicators, market microstructure.

• Experience with tick data, time-series modeling, vectorized backtesting.

• Familiarity with APIs (REST/WebSockets).

• Strong in data pipelines & model lifecycle management.

Quantitative

• Strong math: probability, statistics, optimization, time-series analysis.

• Knowledge of volatility models (GARCH), HMM, clustering.

Tools

• Version control: Git

• Model tracking: MLflow / DVC

• Deployment: Docker

• Pipelines: Airflow / Prefect

• Databases: PostgreSQL / MongoDB / Clickhouse

⸻

QUALIFICATIONS

• B.Tech / M.Tech / MSc / PhD in CS, AI/ML, Quant, Statistics, Mathematics, or related fields.

• Prior experience in trading bots, ML projects, or quant research is preferred.

• (Optional but excellent): Experience in Forex, Options, Crypto or HFT environments.

⸻

WHAT THIS ROLE ENABLES

• Build Optimizers

• Build AI/ML indicators

• Build MetaBots

• Build production-grade algos

• Detect number patterns & market regimes

• Achieve high win-rate, low SL, low drawdown systems

• Scale across prop-firm accounts, multi-asset, multi-region

This is the role that creates the intelligence layer of a modern Quant Desk.