Research internship - Time Series Foundation Models

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.

Overview

Large language models trained on massive corpora drawn from a wide range of domains have found remarkable success when applied to many highly specialized problems. Following this achievement, substantial research has been devoted to the question of whether similar “foundation” models can also be created for time series. Could a transformer model trained on millions of time series from varied domains produce better forecasts of, e.g., returns than a more specialized model?

That is the problem you will explore during this internship. Starting from an assessment of the current state-of-the-art in pre-trained “time-series foundation models”, you will then have the opportunity and resource support to explore what those models are capable of in practice. These investigations will then guide the future operationalization of TSFMs within CFM.

Internship goals

1. Assess the current landscape of existing TSFMs to identify promising models and architectures
2. Benchmark off-the-shelf (i.e. pre-trained) solutions on prediction problems relevant to the work done at CFM
3. Explore parsimonious architectures for in-house TSFM training and/or distillation and fine-tuning of extant models

Ideal candidate 

• Pursuing a graduate degree (Masters or PhD) in a quantitative field
• Strong interest in machine learning and finance
• Proficient in Python for data analysis and machine learning

Location

• New York, New York

Time period

• 10-12 weeks, from late May to early August, 2026

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.