Description and Requirements
Role Overview
We are seeking a Windows-focused Software Engineer to build agent-driven automatic computer use capabilities that can observe, reason, and take actions on Windows PCs. This role combines deep Windows system engineering with LLM-powered agent integration, enabling intelligent, safe, and automated computer interactions.
You will work on software agents that leverage LLMs for reasoning and decision-making, while executing actions through Windows OS APIs and services.
Key Responsibilities :
Windows Computer Use & Automation
- Design and implement agent actions that interact with Windows OS, applications, and system services
- Build reliable computer use primitives such as application control, system configuration, file operations, and window management
- Integrate with Windows APIs, services, and background tasks
- Ensure agents function correctly across user sessions, power states, and device conditions
LLM Integration & Agent Intelligence
Integrate LLMs into agent workflows for task planning, decision-making, and intent interpretationImplement prompt templates, tool-calling patterns, and structured outputsHandle fallbacks between LLM-based reasoning and deterministic logicOptimize LLM usage for latency, cost, and reliabilityAgent Execution & Reliability
Implement execution logic including retries, rollback, and error handlingOptimize system performance, power usage, and responsivenessSupport long-running and event-driven agent workflowsSecurity, Privacy & TrustRespect Windows security boundaries and permission modelsImplement safeguards to ensure transparent and user-controlled automationContribute to logging, auditing, and explainability of agent actionsCollaboration
Partner closely with Agent Platform, AI, UX, and Android teamsParticipate in architecture reviews and cross-platform design discussionsHelp define best practices for AI-driven computer use automationBasic Qualifications
4+ years of professional software engineering experienceStrong experience building Windows desktop or system-level softwareProficiency in C++ and / or C# (.NET)Hands-on experience with Windows Services, background execution, or system APIsAt least 2 years of experience integrating and using Large Language Models (LLMs) in production or near-production systems, including : Calling LLM APIs or frameworksIntegrating LLMs into application workflowsHandling structured outputs, error cases, and latency considerationsStrong understanding of multithreading, concurrency, and system debuggingPreferred Qualifications
Experience with agent-based automation or computer use systemsAdvanced LLM integration experience, including : Tool / function callingPrompt engineering and evaluationHybrid rule-based + LLM architecturesKnowledge of Win32, WinRT, UWP, WMI, or PowerShellFamiliarity with : Power management and resource constraintsEnterprise or OEM Windows environmentsExposure to AI safety, guardrails, or explainability techniques