AI System and Application Engineer（Intern）

Salary: $12,000 – $15,000 per month

岗位介绍

你将与同事协作完成开源LLM大模型在英伟达和国产异构计算平台的部署、性能评测与调优，并参与公司AI Agent 产品设计与研发，协同团队完成工程项目技术验证与文档输出。

主要职责

• 基于vLLM/SGLang以及英伟达/国产异构计算平台部署大语言模型，完成推理性能测试与优化

• 参与公司AI Agent 产品设计与研发，满足AI办公与AI编程等场景需求。

• 配合团队完成项目技术验证，编写项目相关文档

任职要求

• 计算机、电子工程、人工智能、数据科学相关专业在读硕士；优秀大三及以上本科生亦可

• 熟练掌握 Python、PyTorch

• 熟悉 DeepSeek、Qwen 等主流大模型

• 熟悉vLLM 或 SGLang 推理框架

• 熟悉 Linux、Docker 容器，会使用 AI 编程工具

• 具备良好代码规范意识

• 优秀沟通协作能力，能够独立解决问题

• 热爱 AI 工程化方向

工作语言：普通话

Job Introduction

You will collaborate with teammates to deploy, benchmark, and tune open-source LLMs on NVIDIA and domestic heterogeneous computing platforms. You will also take part in the design and R&D of the company’s AI Agent products, and work with the team to deliver technical verification and documentation for engineering projects.

Key Responsibilities

• Deploy large language models based on vLLM/SGLang across NVIDIA and domestic heterogeneous computing platforms, and conduct inference performance testing and optimization

• Participate in the design and R&D of the company’s AI Agent products to meet the demands of scenarios including AI office and AI programming

• Support the team in completing project technical verification and preparing relevant project documentation

Requirements

• Pursuing a Master’s degree in Computer Science, Electronic Engineering, Artificial Intelligence or Data Science; exceptional undergraduates (Junior year or above) are also considered

• Proficient in Python and PyTorch

• Familiar with mainstream LLMs such as DeepSeek and Qwen

• Hands-on experience with vLLM or SGLang inference frameworks

• Experienced with Linux, Docker containers, and AI coding tools

• Good awareness of coding standards

• Strong communication and teamwork skills with the ability to solve technical problems independently

• Passionate about AI engineering