Filip Jankovic
Chief AI Officer & Cofounder at Musubi
Santa Barbara, California, United States
Summary
👤
Senior🎓
Top SchoolFilip Jankovic is a data science and AI leader with 11 years of experience building scalable ML solutions for digital health and behavior analytics. As Chief AI Officer and Cofounder at Musubi and former Lead Data Scientist at Evidation Health, he designed production-grade time series deep learning models, MLOps pipelines, and risk prediction systems that powered insights for millions. He combines hands-on engineering — including open-source contributions to the tsai time series library where he modernized the codebase for nbdev2 — with product-focused leadership and a track record of patents and publications. Based in Santa Barbara and trained at the University of Michigan, Filip blends academic rigor with startup grit to move complex health AI from research into reliable, ethical production.
10 years of coding experience
9 years of employment as a software developer
MSE Industrial and Operations Engineering, MSE Industrial and Operations Engineering at University of Michigan
Github Skills (9)
pytorch10
fastai10
time-series10
deep-learning10
python9
machine-learning9
faster-rcnn8
mask-rcnn8
transformer7
Programming languages (4)
Github contributions (5)
timeseriesAI/tsai
Oct 2022 - Oct 2022
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
Role in this project:
ML Engineer
ML EngineerContributions:8 commits, 1 PR in 1 day
Contributions summary:Filip's commits primarily involve updating the codebase to be compatible with `nbdev2`. These changes include modifications to notebook structures, import statements, and potentially build processes. This indicates a focus on maintaining the project's development environment and ensuring the seamless integration of new versions of dependency libraries, specifically within a time series deep learning context as indicated by the repository's purpose. The changes involve refactoring and adaptations across multiple files and notebooks to adhere to the new version's specifications.
forecastingpythontime-series-analysisstate-of-the-arttime-series
filipj8/FJWebsite
Jul 2017 - Oct 2019
My Personal Webpage: www.filipj.com
Contributions:1 PR, 35 pushes, 5 branches in 2 years 3 months
personal-webpagewebpage
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.