Niklas Von Maltzahn
Head Of Data Science And Analytics
Western Cape, South Africa
Summary
👤
Senior🎓
Top SchoolNiklas Von Maltzahn is a data science and ML leader with nine years of fintech-focused experience, currently heading Data Science and Analytics at JUMO World where he drives AI-powered decisioning across African and Asian markets. He combines deep modeling expertise—from credit default and fraud models to IFRS9 provisioning—with hands-on MLOps and cloud deployment skills to take projects from raw data to production. Niklas leads a cross-functional team of ML engineers and decision scientists, emphasizing faster iteration, reduced error and scalable feature pipelines. An active contributor to Feast’s Spark offline store, he has practical experience optimizing batch writes and remote storage exports, reflecting a rare blend of feature-store engineering and applied decision science. Trained in actuarial science and quantitative finance from the University of Cape Town, he brings rigorous quantitative foundations to pragmatic business problem solving.
9 years of coding experience
4 years of employment as a software developer
Matric Exemption, Matric Exemption at Table View High SchoolBachelor of Business Science (Hons) Actuarial Science and Quantitative Finance, Bachelor of Business Science (Hons) Actuarial Science and Quantitative Finance at University of Cape Town
English, German, Afrikaans
Stackoverflow
1reputation
0reached
1answer
0questions
Github Skills (18)
feature-store10
spark10
python10
data-engineering10
mlops10
data-science9
data-pipelines9
pyspark9
big-data9
data-pipeline9
aws8
machine-learning8
data-quality8
sql7
pandas7
Programming languages (7)
Github contributions (5)
feast-dev/feast
Aug 2022 - Sep 2022
The Open Source Feature Store for AI/ML
Role in this project:
Back-end Developer & MLOps Engineer
Back-end Developer & MLOps EngineerContributions:2 reviews, 7 commits, 14 PRs in 1 month
Contributions summary:Niklas's contributions primarily revolved around enhancing the Spark offline store integration within the Feast feature store. They implemented crucial functionality such as the `offline_write_batch` method and `to_remote_storage`, enabling writing data in batches and supporting remote storage exports. The user addressed issues related to type conversions and data handling, demonstrating expertise in Spark and data pipeline optimization. They also made improvements to the testing framework and added date field support.
pythondata-qualitydata-sciencemlmachine-learning
niklasvm/feast
Aug 2022 - Jan 2025
Feature Store for Machine Learning
Contributions:4 PRs, 68 pushes, 14 branches in 2 years 5 months
pythondata-sciencemachinelearningmachine-learningmlops
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.