About this role
ABOUT CFM
Founded in 1991, we are a global quantitative and systematic asset management firm applying a scientific approach to finance to develop alternative investment strategies that create value for our clients.
We value innovation, dedication, collaboration, and the ability to make an impact. Together, we create a stimulating environment for talented and passionate experts in research, technology, and business to explore new ideas and challenge existing assumptions.
Your Role
Data Referential – Directional is responsible for ensuring the integrity, accuracy and accessibility of data related to the CFM trading universe. It operates at the intersection of data management, technology and finance, managing critical data that drives diversified investment strategies, with a primary focus on derivatives instruments.
We maintain a large universe of FICC derivatives and indexes, each with historical timeseries of prices, derived market data, and referential data. An existing algorithm flags outliers such as price jumps, but today they are only investigated when a product is about to move into production. Operators must then manually review each outlier and decide whether it is a valid event (a legitimate price jump) or a data error to fix (correcting the timeseries with a valid price). This is time-consuming and generates many false positives.
The central project of your internship is to use LLM-based agents and historical News datasets to automatically distinguish real data issues from legitimate market events, so that operators can focus only on the cases that truly require human attention.
Key Responsibilities
- Develop an automated approach, based on AI agents and historical News datasets, that classifies each detected outlier as a legitimate market event or a genuine data issue, in order to reduce false positives.
- Correlate detected outliers with contextual information extracted from News data (sentiment, corporate events) to explain or validate market movements.
- Benchmark your results against historical price validations previously performed manually.
- Handle large-scale, feature-rich News datasets (sentiment scores and other signals) through efficient data processing and feature selection.
- Explore how AI-driven approaches can be integrated into the existing outlier detection and validation workflow, and help build reusable, scalable tooling to support the transition of products into production with less manual effort.
Your Skills
- You are pursuing Master's level studies (or equivalent) in data science, with a focus on dataset quality.
- You have an aptitude for data analysis, problem investigation and the automation of manual processes.
- You are comfortable with Python and with working on large, high-dimensional datasets.
- You are comfortable in both French and English.
- You are motivated, curious and rigorous, with a strong team spirit.
- A plus: experience with large text/News datasets, SQL, financial timeseries and corporate actions, data quality frameworks and validation methodologies.
EQUAL OPPORTUNITIES STATEMENT
We are continuously striving to be an equal opportunity employer and we prohibit any discrimination based on sex, disability, origin, sexual orientation, gender identity, age, race, or religion. We believe that our diversity, breadth of experience, and multiple points of view are among the leading factors in our success.
CFM is a signatory of the Women Empowerment Principles .
FOLLOW US
Follow us on Twitter or LinkedIn or visit our website to find out more about CFM.