Teams at NVIDIA

Lead development of local AI agent frameworks and optimized runtimes on Windows for GeForce RTX PCs. Ensure secure, sandboxed execution and privacy-aware inference routing, collaborate with AI research and driver teams, mentor engineers, and produce production-ready code for autonomous, always-on desktop AI assistants.

Lead development of local AI agent frameworks and runtimes on Windows for GeForce RTX PCs. Optimize GPU-accelerated LLM inference, enforce policy-based privacy and sandboxing, collaborate with research, driver, and open-source communities, mentor engineers, and produce production-ready code and deployment guidelines.

Design, build, and maintain SDKs and CLIs for cloud GPU services; collaborate with cross-functional teams to define requirements; implement RESTful services, ensure high-quality code with unit and integration tests, drive performance tuning, test automation, and document/support software.