Senior Data Scientist

Improved error rate in Speed Limit elements from 24% to 8% by implementing an LLM pipeline on detected objects (with natural lower bound of 6% as image coverage is only 94%)

Extensive ML modeling of Routing Cost Function (objective function, features, hyperparameters, training data generation) which led to setting the foundation for a rebuild of a more flexible setup

Initiated the first Prioritization Framework for Data Curation Ops ($2M annual organizational expenses) which moves away from daily quotas and now optimizes for ‘expected business value per time unit’, achieving around 5-7% efficiency improvement

Close collaboration with Software Engineering & Data Engineering as well as Product & Operations

Developed and implemented startup discovery rankings end-to-end from data acquisition to publishing

Quantified impact of clients' innovation projects with startups through business case calculation totaling over €50m

Recruited engineers, venture analysts, and sales staff, growing a remote-first team from 5 to 28 people within 15 months

Owned financial planning (for over €100k MRR) and maintained investor relations with 14 business angels