Jason Meno

About

ML practitioner with hands-on experience in healthcare time-series modeling (CGM-based blood glucose prediction) including a novel ICA-based blind source separation approach and robust data-cleaning for noisy, missing sensor data. Also built an embeddings + LLM-powered podcast recommendation workflow using YouTube transcript scraping and Vellum AI document indexing, with a strong emphasis on production-grade engineering practices (TDD, monitoring) and realistic rolling validation for forecasting.

Experience

Education

Key Strengths

• Built multi-horizon glucose prediction models from noisy CGM time series data
• Designed novel ICA-based blind source separation approach and benchmarked against multiple baselines/models
• Strong time-series data cleaning pipeline design (deduping, interpolation, smoothing, time-shift alignment)
• Applied RMSE and baseline modeling to evaluate forecasting performance rigorously
• Implemented embeddings-based document indexing + LLM synthesis for podcast recommendations
• Production mindset: TDD, unit-tested modular pipelines, monitoring/alerting with performance metadata
• Validated forecasting model via rolling training simulation to mirror real production behavior and gain stakeholder approval