Make the user's computer dependable when the agent is busy and the person needs it most. You will work close to the operating system.
Not open yet: First team
This work starts when that stage arrives, so there is no application to submit today and we will not pretend otherwise. What is written below is what the role is for and what would make somebody right for it, published early on purpose so you can decide whether it is worth watching.
The work
Build process supervision, resource isolation, permissions, storage integration and background execution. Diagnose problems across CPU scheduling, memory pressure and device drivers. Respect the capabilities and restrictions of each supported operating system.
The milestone
In your first 90 days, ship a supervised local runtime that survives restarts, respects resource budgets and produces useful diagnostics without exposing personal content.
Evidence
Bring strong operating-systems fundamentals and practical experience in Rust, C, C++ or comparable systems tools. Show how you debug concurrency, memory or performance problems rather than listing languages.
Evidence, not credentials. We are describing work you can point at, in whatever form it exists.
The exercise
Investigate a service that stalls under memory pressure and propose a recovery design that preserves acknowledged work.