Control Layer EngineerWe're looking for an engineer to work on the control layer - the system that translates an AI model's intent into precise, reliable actions on a real computer. This means mouse movements, keyboard input, window management, UI element detection, and error recovery across macOS, Windows, and Linux.What you'll doWork on the low-level computer control stack: mouse/keyboard injection, screen capture, coordinate mapping, input simulationImplement UI element detection using accessibility APIs (AXUIElement, UI Automation), DOM/a11y trees, and visual groundingHelp build the abstraction layer that lets our agent operate across OS platforms and application typesTackle reliability problems: element targeting under UI changes, window occlusion, resolution scaling, cross-app focus managementContribute to feedback loops: how does the agent know its action worked? How does it recover when something unexpected happens?Work closely with the model and planning team on the interface between intent and executionYou might be a fit ifYou've built OS-level input automation (CGEvent, SendInput, xdotool, or similar)You understand accessibility frameworks - AXUIElement on macOS, UI Automation on Windows, AT-SPI on LinuxYou've dealt with flaky element selectors, timing issues, resolution-dependent coordinatesYou think carefully about reliability and edge casesYou've worked with tools like Playwright, Appium, PyAutoGUI, Hammerspoon, or similarBonusExperience with screen reader internals, remote desktop protocols (RDP/VNC), game automation, LLM agent tool-use systems, or mobile device automation (iOS UIAutomation / XCTest, Android UIAutomator / Accessibility).