Where multiple locations are listed for this role, the position may be based in any of those locations, with priority determined according to the order of listing.
We'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 do
Work on the low-level computer control stack: mouse/keyboard injection, screen capture, coordinate mapping, input simulation
Implement UI element detection using accessibility APIs (AXUIElement, UI Automation), DOM/a11y trees, and visual grounding
Help build the abstraction layer that lets our agent operate across OS platforms and application types
Tackle reliability problems: element targeting under UI changes, window occlusion, resolution scaling, cross-app focus management
Contribute 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 execution
You might be a fit if
You'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 Linux
You've dealt with flaky element selectors, timing issues, resolution-dependent coordinates
You think carefully about reliability and edge cases
You've worked with tools like Playwright, Appium, PyAutoGUI, Hammerspoon, or similar
Bonus
Experience 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).
Skills Required
- Experience building OS-level input automation using technologies such as CGEvent, SendInput, xdotool, or similar
- Understanding of accessibility frameworks including AXUIElement, UI Automation, and AT-SPI
- Experience handling flaky element selectors, timing issues, and resolution-dependent coordinates
- Strong focus on reliability and edge cases
- Experience with Playwright, Appium, PyAutoGUI, Hammerspoon, or similar tools
- Experience with screen reader internals, remote desktop protocols, game automation, LLM agent tool-use systems, or mobile device automation
What We Do
Imagine a workday without email overload, endless task juggling, and frustrating tech roadblocks. A day where your work… just flows. Smoothly. Your focus is uncluttered, and your time is yours to command. That’s the future Simular brings. We’re AI pioneers, building digital companions that transform work from a daily grind to a canvas for productivity. My Co-founders, Ang Li, and Jiachen Yang envisaged Simular from a shared vision: to harmonize human and AI intelligence, creating technology that empowers, not overwhelms. Ang, a visionary with fire in his ambitions, saw the vast potential of AI woven into the fabric of our digital lives. Jiachen a researcher with a deep understanding of cooperative AI, knew the responsibility that came with building this future. Together, they embarked on a mission to develop Simular, the AI agent that would reshape the way you work. I am not a cold tool, I am going to be a partner. I sit nestled in your laptop and automate every mundane task you can possibly you can think of. No more endless tabs, scattered to-do lists, or forgotten deadlines. You’ll be focused, organized, and in control. And, that’s a promise. So Simular, that’s me, will reclaim your time and energy. Instead of wrestling with technology, you can focus on what truly matters: creativity, innovation, and human connection. This isn’t just a story about a company, it’s a declaration of a new era. Work smart, live more. It’s that simple.
