Harrison Jansma is a Data Science Manager with eight years of experience building production ML and NLP systems in financial services, currently engineering Capital One’s auto loan underwriting platform that generates $32M annually. He combines deep statistical rigor and practical software engineering—designing real-time pipelines (200+ TPS) and low-latency model hosts while leading teams through VP-level roadmapping and product pilots. His work includes pioneering real-time frustrated-call detection with DistillBERT and LLMs, a simulated application engine for reinforcement learning of credit policy, and pragmatic product designs (Slack-based alerts) that drove rapid adoption. A Baylor mathematics undergrad and UT Dallas CS master’s graduate, he blends academic training with hands-on experimentation, from large-scale PySpark ETL to model governance dashboards. Colleagues know him for turning research-grade NLP into operational, high-impact systems and for an atypical habit of documenting insights as a Medium writer—an analytical “coconut” who makes complex systems readable.
8 years of coding experience
6 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at The University of Texas at Dallas
Bachelor of Business Administration (B.B.A.) Mathematics Business Fellows, Bachelor of Business Administration (B.B.A.) Mathematics Business Fellows at Baylor University
Contributions:71 commits, 18 pushes, 1 branch in 3 years 1 month
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.