Senior DevTech Engineer - Windows LLM and GenAI Open-Source Ecosystem

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 like PyTorch or llama.cpp.
• Experience with CUDA and NVIDIA's Nsight GPU profiling and debugging suite.
• Strong verbal and written communication skills in English and organizational skills.
• Excellent interpersonal skills.
• Some travel required for conferences and on-site visits with external partners.

Nice to Haves:

• Experience with GPU-accelerated AI inference using NVIDIA APIs such as cuDNN, CUTLASS, TensorRT.
• Confirmed expert knowledge in Vulkan and/or DX12.
• Familiarity with WSL2 and Docker.
• Detailed knowledge of the latest generation GPU architectures.
• Experience with AI deployment on NPUs and ARM architectures.

What you'll be doing:

• Improve Windows LLM & GenAI user experience on NVIDIA RTX.
• Engage with internal teams and external OSS maintainers to align on OSS enhancements.
• Solve end-to-end LLM & Generative AI GPU deployment challenges.
• Analyze most demanding GPU-accelerated AI applications utilizing profiling tools.
• Provide trainings, develop sample code, and host presentations on efficient AI deployment.
• Guide AI application developers on adopting DL frameworks for optimal GPU performance.
• Collaborate with GPU driver and architecture teams to influence next-gen GPU features.

Perks and Benefits:

• Highly competitive salaries.
• Extensive benefits package.
• Work environment promoting diversity, inclusion, and flexibility.