Hi! I’m Roone Ruanaidh.

I work at the intersection of AI, infrastructure, and economics.
I build AI systems for environments where affordability, observability, and assurance are non-negotiable.

My main research project, Envelope, lives at that intersection.
Envelope researches how predictable the cost of agentic work becomes when a model can invoke programmatic capabilities that advance a task outside its context window. You can read more on the Envelope page or my GitHub.

I’m currently looking for my next role.

I’m drawn to low-level systems and high-performance computing, whether that be building and benchmarking agentic workloads or profiling inference performance across various model and hardware combinations.

I believe AI’s engineering and economic trade-offs are inseparable, and the organizations that resolve that tension will deliver the greatest benefit and lead the market.

Ultimately, what matters most to me is working on hard problems that aren’t fully understood yet as part of an ambitious and collaborative team.

If that sounds like your team, I’d love to connect!

Outside of work I’m a prolific poet and reader, and there’s almost always music playing in my home. Sometimes my own, as a self-taught blues guitarist of 18 years. I also love to cook: most weekends start at my local farmers’ market and end with ingredients for the week prepped.
If I’m not doing one of those, I’m walking my dog, Athena, or keeping company with my cats, Opal and Zooey (who were actually born on my front porch).

My email, X, GitHub, and LinkedIn are linked below — reach out anytime!