AI Computing Development Intern, TensorRT-LLM - 2027
Salary not listed • China, Shanghai • Internship
Posted 1mo ago
Remote Work Policy
On-site
Employment Type
Internship
Categories
LLM Engineer
About the job
NVIDIA is seeking a TensorRT-LLM Software Development Engineering intern to join its AI Computing team. This role involves contributing to the development of inferencing software that powers deep learning breakthroughs in areas like LLM, ChatGPT, and Generative AI. The ideal candidate will work in a fast-paced, delivery-focused team and possess excellent interpersonal skills.
Responsibilities
- Develop scalable inferencing software for multiple platforms, focusing on functionality and performance.
- Conduct performance analysis, optimization, and tuning.
- Stay updated on AI academic developments and update TensorRT-LLM accordingly.
- Provide feedback on architecture and hardware design.
- Collaborate with software, research, and product teams to influence machine learning inferencing direction.
- Publish key research findings in scientific conferences.
Requirements
- Currently pursuing a Master's or higher degree in Computer Engineering, Computer Science, Applied Mathematics, or a related computing field.
- Possess relevant software development experience.
- Proficient in C/C++ programming and software design, including debugging, performance analysis, and test design.
- Demonstrate strong curiosity in artificial intelligence and awareness of deep learning advancements (LLMs, generative, recommender models).
- Experience with deep learning frameworks such as TensorFlow and PyTorch.
- Proactive and capable of working independently.
- Excellent written and oral communication skills in English.