Ethan Fang
Based out of the Bay Area. I spend most of my time in math modeling, AI research, and engineering.
I graduated from Case Western Reserve University in May 2026 with a dual BS/MS degree in computer science. During my time there, I cofounded the quant finance club, grew the tennis club to record participation, and did lots of research.
Currently, I am a quantitative analyst at KeyBank where I model expected loss for the bank's portfolio. I enjoy doing research in my spare time, focused primarily on ML and financial markets.
I am passionate about researching and building technologies that create meaningful real-world impact. My interests include sustainability, human-centered AI, and athletic performance.
Work
-
KeyBank · Lead Quantitative Analytics Associate
-
Vantura · Founding Engineer
-
Case Western Reserve University · Research Assistant
-
Clarity · Growth
-
KeyBank · Quantitative Analytics Intern
-
MISCO Refractometer · Engineer Intern
Research
-
Perpetual Text Generation
Research on extending LLM generation past the natural stopping point. Introduces a method that detects emergent EOS tokens, backsteps, and applies dynamic temperature adjustment — doubled for exploration, then annealed back to baseline. Pushes Llama2-7B-chat ~1,000 additional coherent tokens past where it would otherwise halt.
-
Q-Learned CNN Branch Selection
Reinforcement-learning agent that dynamically selects convolutional branches at inference time, trading FLOPs for accuracy on a per-sample basis. Trained with Q-learning over a branching CNN backbone.
Projects
-
A morning briefing app that turns the news, sports, and stocks you follow into a short audio podcast you can listen to on your way out the door. Backed by ElevenLabs, Founder University, and CWRU.
blog post ↗ -
iLiterate
A language-learning site for second-generation readers rebuilding literacy in their native language — lessons, flashcards, and a speed reader, built on Next.js and Supabase with OpenAI, Gemini, and ElevenLabs.
-
XRDimage
Python package that identifies alpha and beta rings in noisy X-ray diffraction images so researchers can run downstream analysis. Published to PyPI.