Mira Chen
Infrastructure Lead · 2 posts
I work on inference scheduling and GPU efficiency at Nexora. Before this I spent eight years on distributed systems. I write about the unglamorous engineering that makes models fast in production.
FollowLatest from Mira Chen 2 ARTICLES
Engineering
How we cut agent inference latency to 82ms
A look inside the scheduling, caching, and routing work that took our median agent response time below the 100ms threshold — and w...
Product
Introducing Guardrails 2.0
Guardrails 2.0 brings policy-as-code, streaming enforcement, and per-tool scopes to every Nexora agent.
Ship inference that scales
Deploy your first model on Nexora in minutes. Pay only for what you run.