Emmanuel Watila

I’m a software engineer and AI safety researcher. My work sits between product engineering, empirical model evaluation, and research tooling: I build useful systems, then study how they behave when correctness, uncertainty, and trust matter.

I’ve built Readlater, an AI-powered read-it-later platform for saving, organizing, searching, summarizing, and resurfacing important reading across a browser extension, web app, and MCP workflows. I also developed Krisis, a clinical LLM evaluation framework for testing whether models can calibrate their confidence, abstain, defer, and express uncertainty in high-stakes medical reasoning tasks.

I studied Computer Engineering at the University of Maiduguri, where my thesis explored hybrid quantum-classical neural networks. Since then, I’ve worked across full-stack product engineering, front-end systems, healthcare-adjacent platforms, open-source data tooling like breadroll, and technical writing. I care about rigorous evaluation, type-safe architecture, and interfaces that make complex systems easier to reason about.

Doing

I’m currently researching AI Safety (Supervised Fine-Tuning with Low-Rank Adaptation, Model Interpretability, Black Box Evluation), Quantum Machine Learning. I’m also actively learning Digital Signal Processing in Python.

Have a cool project?, feel free to hit me up.