Python Vision-Based Desktop/browser Agent GUI Automation

be ready to share your screen and do a test on your first call We are looking for an expert Python developer to build a tool must operate at the OS/GUI layer, moving the mouse and typing on the keyboard exactly like a real human operator. we do not want to use traditional web testing frameworks like Selenium, Playwright, or Puppeteer. Responsibilities: * Develop a Python automation script utilizing OS-level tools (e.g., PyAutoGUI or PyDirectInput). * Integrate a vision model API to visually analyze screen captures, identify on-screen targets, and output spatial (x, y) coordinates. * Ensure the tool can run directly on our active desktop session using our pre-logged-in browser profile.