Requirements:

5+ years of professional experience in local GPU deployment, profiling, and optimization.
BS or MS degree in Computer Science, Engineering, or related field.
Strong proficiency in C/C++, Python, software design, and programming techniques.
Familiarity with and development experience on the Windows operating system.
Proven theoretical understanding of Transformer architectures, specifically LLMs and Generative AI, and convolutional neural networks.
Experience working with open-source LLM and GenAI software.
Experience with CUDA and NVIDIA's Nsight GPU profiling and debugging suite.
Strong verbal and written communication skills in English, organizational skills, logical approach to problem-solving, time management, and task prioritization skills.
Excellent interpersonal skills.
Some travel required for conferences and on-site visits with external partners.

What you'll be doing:

Improve Windows LLM & GenAI user experience on NVIDIA RTX by enhancing OSS software features and performance.
Engage with internal and external teams to prioritize OSS enhancements.
Collaborate on local end-to-end LLM & Generative AI GPU deployment challenges.
Utilize profiling and debugging tools for analyzing demanding GPU-accelerated AI applications.
Develop sample code, host presentations, and guide developers on efficient AI deployment.
Collaborate with GPU driver and architecture teams to influence next-gen GPU features.

Experience with GPU-accelerated AI inference using NVIDIA APIs like cuDNN, CUTLASS, TensorRT.
Expert knowledge in Vulkan and/or DX12.
Detailed understanding of the latest GPU architectures.
Experience with AI deployment on NPUs and ARM architectures.

Opportunity to work with cutting-edge technologies at a leading company in visual computing.
Engage with strategic partners and internal teams on innovative AI models and functionality.
Promote creativity and collaboration in a dynamic work environment.
Equal opportunity employer promoting diversity and a challenging work culture.