AI Computing Software Development Intern, LLM Inference - 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 Software Development Engineer to contribute to the TensorRT LLM and TensorRT Edge LLM projects within its AI Computing team. This role involves developing inferencing software that powers deep learning-based AI advancements, including LLMs and Generative AI. The ideal candidate will work in a fast-paced, delivery-focused environment 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 academic advancements in artificial intelligence and large language models.
- Provide input on architecture and hardware design and development.
- Collaborate with software, research, and product teams to influence machine learning inferencing direction.
- Publish significant 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.
- Demonstrate excellent C/C++ programming and software design skills, including debugging, performance analysis, and test design.
- Exhibit strong curiosity in artificial intelligence and awareness of deep learning trends like LLMs, generative, and recommender models.
- Have experience with deep learning frameworks such as TensorFlow and PyTorch.
- Be proactive and capable of working independently.
- Possess excellent written and oral English communication skills.