Quantitative Researcher (Monetisation)

Thurn Partners; Greater London; On-site; GBP 150,000 - 230,000; Full time

Job summary

Thurn Partners, London-based quantitative trading firm, is building a specialist team focused on alpha blending, monetisation, and optimisation. You will work with a library of raw signals from the alpha research group to produce live, risk-bearing strategies.

You will own the live optimisation, risk, and execution interfaces, iterating against PnL, adjusting signal weights, and refining capital efficiency in production settings.

Qualifications

• Strong background in statistical modelling and ML, with optimisation and portfolio construction.
• Experience in signal combination or systematic portfolio construction, ideally in a mid-frequency setting.
• Proficiency in Python; C++ and HPC experience are a plus.
• Track record of taking research into production and generating live PnL.
• Experience with financial time-series analysis and market microstructure is preferred.

Responsibilities

• Combine and weight a large set of raw alpha signals into coherent strategies.
• Build and own the optimisation layer: portfolio construction and capital allocation.
• Model and minimise trading costs, considering market impact and capacity constraints.
• Iterate on live performance: monitor PnL, diagnose alpha decay, rebalance weightings.
• Work with infrastructure and execution teams to deploy the strategies in production.
• Own the live risk profile of the blended book and manage exposures.

Skills

Statistical modelling

Machine learning

Portfolio construction

Python

C++

Productionization

Time-series analysis

Market microstructure

Job description

Company: A leading quantitative proprietary HFT firm expanding into mid-frequency strategies across global equities, futures, and derivatives markets.

Location: London

The role: The firm is building a specialist team focused on alpha blending, monetisation, and optimisation. The team works with a library of raw signals from the alpha research group to produce live, risk-bearing strategies, with exposure from signal combination up to execution.

Responsibilities

• Combine and weight a large set of raw alpha signals into coherent, tradable strategies, managing signal correlation, overlap, and interaction.
• Build and own the optimisation layer: portfolio construction, capital allocation, and position sizing across signals and markets.
• Model and minimise the cost of trading, accounting for market impact, transaction costs, and capacity constraints when translating signals into positions.
• Iterate on live performance: monitor PnL, diagnose alpha decay, rebalance signal weightings, and improve the capital efficiency of the book over time.
• Work with infrastructure and execution teams to deploy the combined strategies into production and refine them under live conditions.
• Own the live risk profile of the blended book, conducting rigorous risk assessment and managing exposures.

Requirements

• Strong background in statistical modelling and machine learning, with particular value placed on optimisation, ensemble methods, and portfolio construction (e.g. convex optimisation, mean-variance and its extensions, gradient boosting, neural networks).
• Demonstrable experience in signal combination, alpha mixing, or systematic portfolio construction, ideally in a mid-frequency setting.
• Proficiency in Python; C++ and experience in high-performance computing environments are a plus.
• A track record of taking research into production and generating live PnL is highly valued.
• Experience with financial time-series analysis, market microstructure, or transaction cost modelling preferred.