Noam Michael

Noam Michael

Researcher & Builder

Current Work

What I'm currently focused on:

AI Engineer — Robyn Dawes Institute

Building an AI-native pipeline to source, code, extract, and analyze structured data from academic papers for meta-analysis. Improved paper field extraction by 30% by improving OCR systems and LLM field extraction. (FastAPI, Next.js, Supabase, Docker).

Engineer — Askademia

Building an interactive note-taking environment that helps students capture, organize, and revisit lecture content more effectively.

Research Assistant — UC Berkeley Haas

Continuing research on confidence calibration in large language models under Prof. Don Moore. Developing computationally efficient methods for quantifying LLM uncertainty and flagging over-confident behavior for downstream fine-tuning.