Quantitative Researcher

About Millennium

Established in 1989, Millennium is a global alternative investment firm recognized for its continuous evolution, innovation, and emphasis on delivering results for its investors. The company fosters an environment where employees enjoy independence coupled with robust global collaboration, disciplined risk management, and opportunities for continuous professional growth and expertise enhancement.

About the Execution Services Team and Central Liquidity Strategies

The Execution Services team ensures high-quality trading support across various products and geographic regions, focusing on enhancing execution quality, efficiency, and providing portfolio managers with decision-making tools. Within this unit, the Central Liquidity Strategies (CLS) group develops models and a research platform supporting CLS trading by harnessing quantitative research, live analytical insights, and close cooperation with traders and portfolio managers involved in global equities markets.

Responsibilities

• Develop, calibrate, and implement models relating to market microstructure, factor risk, transaction cost evaluation, and alpha signals, ensuring consistent robust performance across US, EMEA, and APAC equity markets.
• Manage and monitor model lifecycles, including tracking performance accuracy, conducting live versus historical data reconciliations, analyzing model drift and decay, recalibrating models, and determining when to retire outdated models.
• Produce and maintain high-quality production code adhering to engineering standards such as unit and integration tests, documentation, automation, and continuous integration/continuous deployment (CI/CD) pipelines.
• Collaborate with team members to influence the design, direction, and structural architecture of the research platform.
• Work closely with traders and portfolio managers to comprehend business requirements and validate model outputs during production stages.

Requirements

• At least six years of experience conducting quantitative research within a financial environment, accompanied by a demonstrated impact through production-level model delivery.
• Possession of a PhD or Master’s degree in quantitative fields such as Statistics, Machine Learning, Physics, Mathematics, Computer Science, or Financial Engineering.
• Proficient understanding of statistical and machine learning models, with practical expertise in techniques like gradient-boosted trees, deep learning using PyTorch, and time-series analysis.
• Advanced technical proficiency in Python and kdb+, with preference for competency in both, for research and analytical purposes.
• Familiarity with tools and environments such as Git, Unix/Linux, Bash scripting, and CI/CD workflows.
• Excellent communication capabilities to clearly explain complex technical concepts in a concise manner.
• Innovative and practical research mindset capable of transforming ideas into production-ready models.
• Additional experience in equity execution, trading operations, live analytics, PyKX, distributed model training, or cloud-based tools is advantageous.