AI Computing Software Development Intern, LLM Inference - 2027
Core
Develop robust inferencing software for TensorRT LLM and TensorRT Edge LLM projects, scaling functionality and performance across multiple platforms.
Role type
Software Development Engineer Intern (LLM Inference)
Builds
GPU-accelerated deep learning inference software for NVIDIA product lines
Domain
AI Computing / Deep Learning / Large Language Models
Deliverable
production ML models
Required skills
C/C++ programming, software design, performance analysis, debugging, test design, deep learning frameworks (TensorFlow, PyTorch), academic research awareness
Preferred skills
Experience with generative AI models, ability to publish scientific results, proactive work style
Technologies
TensorRT, TensorFlow, PyTorch, C, C++
Responsibilities
Craft and develop robust inferencing software, perform performance analysis and optimization, follow academic developments in AI/LLMs, provide feedback on architecture and hardware design, collaborate with software and research teams, publish key results in scientific conferences
Seniority
Intern
