001

Applied AI Researcher

Oshen Davidson

I use data science and machine learning to understand LLMs' behavior and the impact it has on society.

Oshen Davidson
About

Hi! I'm Oshen

I’m currently the Head of Research at AirOps, where I study how large language models are changing the way people find information and make decisions with AI.

I’ve always been drawn to questions that sit just outside what I already know. Growing up during the period when the internet shifted from something people used at work or school to something woven into everyday life gave that curiosity a direction. It made it hard not to notice how much technology shapes culture, communication, and the way people understand the world.

That interest eventually led me to start my career in search engine optimization, where I saw how technical systems influence what people see, trust, and choose. Since then, my work has expanded across growth, research, and product, but the underlying focus has stayed the same: understanding how the internet shapes what people find, learn, believe, and act on.

I’m most interested in the space between how systems are built and how people actually use them. I like finding patterns, making sense of uncertainty, and looking at the same question through a technical, social, ethical, and product lens. The problems that pull me in are generally ambiguous and high-stakes: systems that affect what people know, how they decide, and how information moves through the world. My goal is to make those systems easier to understand, question, and improve.

More about me →

My Thoughts on AI

LLMs are evolving at a pace that is reshaping how people find information, make decisions, and do their work. I find that both exciting and sobering. The acceleration means new capabilities surface faster than most people can evaluate them, and the systems generating those capabilities are already influencing what people believe, what they act on, and how much they can trust what they're reading. That's why I study how these systems retrieve, select, and generate information. Part of that work is practical: helping businesses and brands understand how they show up in AI-generated answers.

But the larger reason is that understanding how these systems actually function is the foundation for understanding their risks, their security implications, and the ethical questions they raise about accuracy, transparency, and accountability. These systems are already mediating how people navigate their health decisions, their finances, their children's education, their understanding of the world around them, whether they realize it or not. I want to be part of making sure that mediation is studied, understood, and held to a standard that protects people while still giving them access to what this technology makes possible.

Specimen 001 · citation behavior
Surviving the Citation Gate: What ChatGPT Cites When Buyers Are Asking
Collected Mar 2026
Read the study →
Specimen 002 · citation behavior
Inside ChatGPT's Search-to-Citation Funnel: Where Pages Lose Visibility
Collected Mar 2026
Read the study →
Specimen 003 · ugc
Community Platforms and UGC as Citation Sources in AI Search
Collected Nov 2025
Read the study →

As Featured In

  • Zyppy
  • Search Engine Land
  • MSN
  • eMarketer
  • MSN Deutschland
  • Forrester