Nicolas Knudde
Algorithmic Credit Trading Associate
Paris, Ile-de-France
Summary
👤
Senior🎓
Top SchoolNicolas Knudde is an Algorithmic Credit Trading Associate at JP Morgan with nine years of experience blending probabilistic machine learning and quantitative finance to build production market-making and pricing strategies. He holds a PhD in Machine Learning from Ghent University and a strong Engineering Physics background, bringing deep expertise in Bayesian methods and Gaussian Processes to trading problems. Nicolas has applied research in industry settings through internships at Amazon and JP Morgan and contributed risk-aware portfolio optimization code (CVaR) to a well-regarded open-source Python library. Based in Paris, he combines hands-on model development and deployment with active inventory and risk management in credit markets. Colleagues describe him as a practitioner who turns advanced research into robust, production-ready trading systems.
9 years of coding experience
5 years of employment as a software developer
Master of Science - MS, Engineering Physics, Master of Science - MS, Engineering Physics at KTH Royal Institute of TechnologyBachelor of Science - BS, Engineering Physics, Summa Cum Laude, Bachelor of Science - BS, Engineering Physics, Summa Cum Laude at Ghent UniversityScience-Mathematics, Magna Cum Laude, Science-Mathematics, Magna Cum Laude at Sint-Paulusinstituut
English, Swedish, French, Dutch
Github Skills (14)
financial-analysis10
pandas10
cvxpy10
python10
optimisation10
quantitative-finance10
optimization10
numpy10
algorithmic-trading9
pytest9
testing9
stock-trading8
finance8
trading8
Programming languages (3)
Github contributions (5)
robertmartin8/PyPortfolioOpt
Jan 2021 - Jan 2021
Financial portfolio optimisation in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity
Role in this project:
Data Scientist
Data ScientistContributions:7 commits, 2 PRs, 4 comments in 9 days
Contributions summary:Nicolas primarily contributed to the implementation and testing of Conditional Value at Risk (CVaR) optimization within the `pyportfolioopt` library. This included adding a new `CVar` class with supporting methods for optimization, validating returns and expected returns data, and integrating it into the existing framework. The user also added tests to verify the functionality of the CVaR implementation, demonstrating a focus on financial portfolio optimization and risk management techniques. Furthermore, the user refactored the code to inherit from the `EfficientFrontier` class, improving code organization and functionality.
pythonportfolio-optimizationriskhierarchicalportfolio-optimisation
nknudde/GPflowOpt
Jul 2017 - Sep 2017
Contributions:55 pushes, 6 branches in 2 months
gpflowoptimizationmachine-learningbayesian-optimizationbayesian
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.