INTERNSHIP DETAILS

Memory-Augmented LLMs for Financial Text - Internship

CompanyCapital Fund Management
LocationJärvenpää
Work ModeOn Site
PostedNovember 12, 2026
Internship Information
Core Responsibilities
Design and implement strategies for incrementally updating a compact memory representation for financial documents. Evaluate these representations for faithfulness and their effectiveness in downstream financial prediction tasks.
Internship Type
full time
Company Size
541
Visa Sponsorship
No
Language
English
Working Hours
40 hours
Apply Now →

You'll be redirected to
the company's application page

About The Company
Capital Fund Management (CFM) is a successful alternative investment manager and a pioneer in the field of quantitative trading applied to capital markets across the globe. Our methodology relies on statistically robust analysis of terabytes of financial data for asset allocation, trading decisions and automated order execution. CFM is an appealing career destination for highly-talented and passionate PhDs, IT engineers and experts from around the world. Our people can rely on original theoretical insight accumulated over 30 years of market experience, as well as cutting-edge technology and disciplined approaches. These fundamentals allow us to foster the creation of exciting opportunities and state-of-the-art trading strategies. Our people’s diversity and dedication contribute to CFM’s unique culture of research, innovation and achievement. The company is regulated by AMF, the SEC and the CFTC, with assets under management of $26.6 billion (April 2026).
About the 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

How Much History Does an LLM Need? Memory-Augmented Language Models for Financial Text 

Financial text about a company accumulates continuously over years. Today's language models typically process this history either by feeding in as much as fits in their context window, or by splitting it into independent chunks. Both approaches have well-known limitations, especially as history grows long and needs to stay historically consistent. 

This internship explores an alternative: building a compact, incrementally updated memory of a company's disclosure history, one that is updated as new documents arrive rather than fully re-read each time. 

The central question is twofold: 

  1. Does a long disclosure history help understand or predict a company's future, compared to only recent information? 

  1. If so, what is the best way to represent and maintain that history over time in a language model? 

Key Responsibilities

  • Design and compare strategies for incrementally updating a compact memory representation as new documents arrive. 

  • Build comparison baselines, including a retrieval-based system. 

  • Evaluate the resulting representations both for faithfulness to the source documents and for usefulness on a downstream financial prediction task. 

  • Read and implement research papers (a significant part of the work). 

Your Skills

Required 

  • Final-year engineering or Master's student in NLP, Machine Learning, Applied Mathematics, or Computer Science.  
  • Strong Python skills, including PyTorch. 
  • Solid understanding of LLMs and sequence modeling. 
  • Ability to read and implement research papers. 
  • Fluent English  

Appreciated 

  • Experience with retrieval-augmented generation, agent memory systems, or reinforcement learning for LLMs. 
  • Interest in financial applications (a bonus). Prior knowledge of finance is not required. 
  • French is a bonus.

 

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.

Key Skills
PythonPyTorchNLPMachine LearningApplied MathematicsComputer ScienceLLMsSequence ModelingRetrieval-augmented generationAgent memory systemsReinforcement learningFinancial analysis
Categories
TechnologyData & AnalyticsSoftwareFinance & AccountingScience & Research