002 Hey there, I'm Oshen \o
At AirOps, I study how LLMs work as search systems: how they retrieve information, cite sources, generate responses, and behave differently from traditional search indexes. My work is split between research and building, from publishing studies on AI search behavior to creating pipelines, benchmarks, prediction models, and product features that bring those findings into the platform.
Outside of work, you can usually find me watching Jeopardy, going deep on a new hobby, tinkering with side projects, or asking way too many questions about how something works.
Most of my work starts with curiosity about how something works.
I like figuring out why a system behaves the way it does, what signals shape the outcome, and what would make it easier for people to understand or use. From there, I follow that thread through research, data, testing, and building until the answer becomes clearer.
While the format may change, my underlying goal remains the same: help people understand complex systems more clearly, use them more confidently, and build better ways to measure and improve them.
Areas of Expertise
I study how LLMs operate and behave as search systems, including how they interpret questions, retrieve context, generate responses, and influence how users search for, find, and interact with information.
I build reusable data pipelines, datasets, and predictive models that turn search, model, and product behavior into measurable signals.
I design research studies, evaluations, benchmarks, and scoring systems that make model behavior easier to test, compare, and improve.
I translate research findings into product direction, internal tools, dashboards, feature concepts, and clear guidance for technical and non-technical teams.
If something here resonated, I’d love to hear from you. I’m always open to talking about AI search, research collaborations, advisory work, or interesting problems that don’t fit neatly into a category.