Inactive
N

Nio

Automotive-grade SoC designer for autonomous driving

LLM Algorithmic Optimization Engineer Intern

Natural Language Processing & LLMsPosted on Jun 13
Internship · Fall 2026San Jose, CA, USA$38 - $46 /hrIn-person

About the Job

Requirements

  • Currently pursuing or completed a PhD or Master's degree in Computer Science, Computer Engineering, Applied Mathematics, Communications, Electronics, or a related field, with relevant research projects and publications.
  • Strong understanding of GPU and NPU architecture and optimization techniques to identify and address bottlenecks.
  • Proficiency in LLM and VLM architectures and algorithms, with familiarity with transformer-based natural language processing, audio, computer vision algorithms, and technologies.
  • Proficiency in Python and experience with artificial intelligence-related training and inference tools such as PyTorch.
  • Proficiency in C and C++ programming and familiarity with at least one commonly used LLM inference engine.
  • Hands-on experience with model-serving frameworks such as Open Neural Network Exchange (ONNX).
  • Familiarity with debugging code in distributed computing environments.
  • A Master's degree plus three years of relevant industry experience may qualify for the preferred pathway.

Responsibilities

  • Conduct research and apply cutting-edge technologies to optimize Large Language Models and multimodal models, including exploring and implementing core algorithmic optimization on heterogeneous architectures for highly efficient LLM inference and deployment across distributed and heterogeneous hardware environments.
  • Optimize models from a systems perspective for efficient deployment in the vehicle's digital cockpit and advanced driving domain.
  • Collaborate with cross-functional teams to integrate optimized models into real-world automotive applications.
  • Contribute to the full pipeline from research, development, and testing through deployment on hardware, including GPUs and other distributed systems.

Desired Qualifications

  • Experience in inference optimization techniques of deep learning models or libraries on hardware architectures.
  • Familiarity with microkernel architecture, Linux kernel, hypervisor, middleware, and application framework.
  • A strong publication record with high-impact, innovative papers.
  • Experience in LLM inference optimization on resource-constrained edge devices.

About the Company

Nio

Automotive-grade SoC designer for autonomous driving

GeniTech designs and develops high-performance automotive system-on-chips for autonomous driving. Its NX9031 SoC uses a 5nm automotive process with 50+ billion transistors, includes a high-dynamic-range ISP and a heterogeneous many-core pool, and is built with a full-stack in-house approach to tightly synchronize sensors and compute cores for real-time fusion and decision-making. It differentiates itself by combining internal hardware supply to its parent company with external IP licensing and joint ventures, offering both an integrated platform and licensed technology. The goal is to industrialize automotive semiconductors and monetize proprietary compute platforms for autonomous driving through licensing, royalties, and collaborations in automotive and robotics.

Company size
5,001-10,000
Company stage
Early VC
Total funding
$310.3M
Headquarters
Huangpu, China
Founded
2014

Recently Posted Jobs

Explore more opportunities at Nio

See more jobs