Lead of Modeling / Deputy to Head of ML at BHFT

Dubai, Dubai, United Arab Emirates -

Full Time

Start Date

Immediate

Expiry Date

04 Mar, 26

Salary

0.0

Posted On

04 Dec, 25

Experience

10 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Machine Learning, Quantitative Finance, Statistical Analysis, Python, PyTorch, TensorFlow, NumPy, Pandas, Model Development, Model Validation, Signal Validation, Team Leadership, Cross-Functional Collaboration, Algorithmic Trading, Data Engineering, Feature Engineering

Industry

Financial Services

Description

Company Description BHFT is a proprietary algorithmic trading firm. Our team manages the full trading cycle, from software development to creating and coding strategies and algorithms. Our trading operations cover key exchanges. The firm trades across a broad range of asset classes, including equities, equity derivatives, options, commodity futures, rates futures, etc. We employ a diverse and growing array of algorithmic trading strategies, utilizing both HFT and MFT approaches. We’ve got a team of 200+ professionals, with a strong emphasis on technology. Our employees are located all around the world, from the United States to Hong Kong. Although we maintain office spaces, we currently operate as a 100% remote organization. Job Description We are seeking a senior leader to own the Model Layer of our ML-driven quantitative research platform. This role leads architecture design, model development, validation, lifecycle management, and standards for all ML models powering our signal generation pipeline. You will work closely with Quant Research, Feature Engineering, Data Engineering, Trading, and AlgoDev to deliver robust, production-grade predictive models. What You’ll Do Lead the design and evolution of the Model Architecture Portfolio across boosting models, time-series deep learning, GNNs, and advanced architectures such as DeepLOB/DeepOB. Build and maintain leakage-free training pipelines, including IS/OOS splits, walk-forward and rolling validation, and high-quality target engineering. Define validation protocols (IC/Rank IC, decay, stability) and conduct statistical robustness testing. Develop explainability and diagnostics frameworks using SHAP, permutation methods, and feature contribution analysis. Architect ensemble strategies (stacking, blending, regime-switching) and manage routing logic across signals and regimes. Own monitoring, drift detection, retraining schedules, and overall model lifecycle governance. Lead and mentor a team of ML researchers and modeling engineers; establish standards for modeling quality, experimentation, and documentation. Partner cross-functionally to ensure seamless integration of models into production trading systems. Qualifications Must-Have Experience 7+ years in machine learning, including 3+ years in quantitative finance or financial ML. Deep knowledge of ML models. Strong statistical background (bootstrap, t-tests, serial correlation, heteroskedasticity). Experience building real-time or near-real-time ML systems and pipelines. Strong understanding of signal validation (IC, Rank IC, decay, cross-sectional behavior). Solid engineering skills in Python, PyTorch/TF, NumPy, Pandas. Quant & Market Knowledge Familiarity with market microstructure, order book data, and factor exposures. Understanding of PnL decomposition, execution effects, and slippage dynamics. Leadership & Communication Experience leading technical teams and driving modeling strategy. Strong communication, documentation, and cross-functional collaboration skills. Impact & Scope This is a high-impact leadership role overseeing critical components of our ML Factory. You will shape modeling strategy, standards, and architecture across the entire research and production pipeline Additional Information Nice to Have Experience in MFT/HFT environments (intra-day). Publications in ML or quantitative finance. Contributions to open-source ML projects.

Responsibilities

Lead the design and evolution of the Model Architecture Portfolio for ML-driven quantitative research. Oversee model development, validation, lifecycle management, and standards for all ML models powering the signal generation pipeline.