DevTech Engineer - Windows LLM and GenAI Open-Source Ecosystem
Description For DevTech Engineer - Windows LLM and GenAI Open-Source Ecosystem
NVIDIA, a pioneer in visual computing and GPU technology, is seeking a DevTech Engineer to join their team focused on Windows LLM and GenAI Open-Source Ecosystem. This role sits at the intersection of cutting-edge AI technology and GPU computing, where you'll work on improving the user experience of Large Language Models and Generative AI on NVIDIA RTX platforms.
The position offers an opportunity to work with the latest developments in AI technology, specifically focusing on the deployment and optimization of LLMs and Generative AI models on Windows systems. You'll be collaborating with both internal teams and external partners to overcome challenges in deploying modern AI architectures on local workstations.
As a DevTech Engineer, you'll be responsible for enhancing open-source projects like PyTorch and llama.cpp, working on performance optimization, and ensuring maximum GPU utilization. The role combines technical expertise in GPU computing with AI development, requiring both deep technical knowledge and strong communication skills.
The ideal candidate will bring 5+ years of experience in GPU deployment and optimization, along with a strong understanding of AI architectures and Windows development. This position offers the chance to influence the future of AI computing while working with NVIDIA's cutting-edge technology and contributing to the open-source ecosystem.
NVIDIA offers competitive compensation and benefits, promoting a diverse and inclusive workplace. This role provides an excellent opportunity for someone passionate about AI technology and GPU computing to make a significant impact in the field of machine learning and AI acceleration.
Responsibilities For DevTech Engineer - Windows LLM and GenAI Open-Source Ecosystem
- Improve Windows LLM & GenAI user experience on NVIDIA RTX
- Engage with internal product teams and external OSS maintainers
- Work on solving local end-to-end LLM & Generative AI GPU deployment challenges
- Apply profiling and debugging tools for analyzing GPU-accelerated AI applications
- Conduct hands-on trainings and develop sample code
- Guide developers on efficient adoption of DL frameworks
- Collaborate with GPU driver and architecture teams
Requirements For DevTech Engineer - Windows LLM and GenAI Open-Source Ecosystem
- BS or MS degree in Computer Science, Engineering, or related degree
- 5+ years of professional experience in local GPU deployment, profiling and optimization
- Strong proficiency in C/C++, Python, software design, programming techniques
- Familiarity with and development experience on the Windows operating system
- Proven theoretical understanding of Transformer architectures - specifically LLMs and Generative AI
- 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
- Excellent interpersonal skills
- Willingness to travel for conferences and partner visits
Jobs Related To NVIDIA DevTech Engineer - Windows LLM and GenAI Open-Source Ecosystem
