Solution Architecture Intern, AI in Industry

Responsibilities

• Provide technical support to internal developers and external customers to facilitate the adoption of NVIDIA technologies.
• Design and implement optimization strategies for various AI models and business scenarios.
• Set up model training and inference environments, identifying bottlenecks to improve model efficiency.
• Conduct surveys and experiments on learning models to consolidate technical guidelines and research papers.

Requirements

• Pursuing a Bachelor's or Master's in Computer Science, AI, or a related field; or a PhD in ML Infrastructure or data systems for ML.
• Proficiency working in Linux environments with strong programming skills in Python or C++.
• Familiarity with AI models, including language, video, or multi-modality models.
• Proficiency in at least one inference framework (e.g., TensorRT, TRT-LLM, ONNX Runtime, PyTorch, vLLM, or SGLang).
• Strong problem-solving skills and the ability to troubleshoot complex technical issues.
• Ability to collaborate effectively across diverse, global teams.

Preferred Qualifications

• Experience optimizing critical operators such as GEMM and attention mechanisms for different GPU architectures.
• Research experience in Speech LLM training or audio classification.
• Ability to align performance with benchmark data, including KV-cache and multi-modality modeling.
• Familiarity with mainstream inference engines like vLLM or SGLang, or disaggregated LLM inference.
• Experience with SOTA Reinforcement Learning (RL) for reasoning model methods.

About the Company

NVIDIA is a global leader in AI computing and visual technologies. For over 25 years, we have been transforming computer graphics, PC gaming, and accelerated computing. Today, we are defining the next era of computing by leveraging the unlimited potential of AI to power computers, robots, and self-driving cars.