Quantitative Researcher

About Millennium

Millennium is a globally diversified alternative investment firm established in 1989, committed to evolution, innovation, and delivering outstanding results for its investors. The company empowers its staff with autonomy to pursue ideas and provides the support of a global network focused on collaboration, disciplined risk management, and continuous development. This environment fosters expertise growth, adaptability, and lasting impact.

Meet the Team

The Execution Services team facilitates trading across various products and regions, emphasizing execution quality and trading efficiency. Within this team, the Central Liquidity Strategies (CLS) group is responsible for developing models and a research platform powering CLS trading. Their work blends quantitative research, live analytics, and close coordination with traders and portfolio managers in global equities markets.

Role and Responsibilities

• Develop, calibrate, and implement models relating to market microstructure, factor risk, transaction cost analysis, and alpha signal detection, targeting robust and consistent performance across US, EMEA, and APAC equities.
• Manage the entire model lifecycle, which includes monitoring model performance, comparing live and historic outcomes, analyzing drift and decay, performing recalibrations, and deciding on model retirement.
• Produce and maintain high-quality production code adhering to best engineering practices such as unit and integration testing, thorough documentation, automation, and continuous integration/deployment workflows.
• Collaborate internally to influence the design, architecture, and strategic direction of the research platform used by the team.
• Engage closely with traders and portfolio managers to comprehend business requirements and validate the production models’ behaviors.

Qualifications and Skills Required

• Over six years of experience conducting quantitative research in finance, with a proven record of deploying production models that deliver measurable benefits.
• Advanced degree (PhD or Master’s) in Statistics, Machine Learning, Physics, Mathematics, Computer Science, Financial Engineering, or a similar quantitative discipline.
• Strong foundation in statistical modeling and machine learning theory, experienced in applying techniques like gradient-boosted trees, PyTorch-based deep learning, and time-series analysis.
• Proficient programming capabilities in Python and kdb+, utilizing these tools for research and analytical purposes.
• Familiarity with Git version control, Unix/Linux operating systems, Bash scripting, and current CI/CD methodologies.
• Ability to communicate complex technical subjects clearly and succinctly.
• Innovative and practical approach in research, with skill in progressing ideas into production-ready models.
• Additional beneficial experience includes equity execution and trading knowledge, live analytics, use of PyKX, distributed training, and cloud technologies.