LLM大语言模型实习生

ical domains

• Build and optimize applications based on the Large Language Model.

• Evaluate and analyze the effectiveness of Large Language Model in vertical domains.

Key responsibilities:

• Collect and collate domain data: collate texts, codes, data, etc. related to automotive/industrial domain, and clean, annotate and collate them to provide high-quality data base for training and application of Large Language Models.

• Design and implement the application solutions of the Large Language Model: Design and implement the solutions based on the Large Language Model according to the specific application scenarios, such as intelligent customer service system, automatic Q&A system, fault diagnosis system, etc.

• Develop and optimise the training and inference process of the large language model: optimise the training and inference process of the large language model to improve the efficiency, accuracy and interpretability of the model.

• Evaluating and analysing the effectiveness of Large Language Models: Evaluating and analysing the effectiveness of Large Language Models in automotive and industrial applications, and improving and optimising them based on the results.

• Write technical documents and reports: Write documents and reports on the research and development of Large Language Models for automotive and industrial applications, documenting the results of the work and lessons learnt.

• Present compelling and proven stories to team members and stakeholders throughout and after the internship

Qualifications and competencies:

• Undergraduate or graduate student in Computer Science/Data Science/Artificial Intelligence or related disciplines: Solid knowledge of computer science fundamentals and familiarity with data structures, algorithms, programming languages, etc.

• Familiarity with Natural Language Processing (NLP) technologies: Understanding of basic NLP concepts such as word embedding, language modelling, text classification, machine translation, etc.

• Familiar with technologies related to Large Language Modelling (LLM): Understand the basic concepts and application frameworks of LLM, e.g. Transformer, PLM, Prompt Engineering, RAG, Fine Tune, LangChain, etc;

• Deployment experience with major open source LLMs, such as ChatGLM, Llama, etc.

• Relevant project experience: Participated in NLP / LLM related projects, such as chatbots, text generation, Q&A systems, etc.

• Familiarity with Python or other programming languages: Proficiency in writing and developing code in Python or other programming languages.

• Good learning and problem solving skills: able to learn new knowledge and technologies quickly and solve problems independently.

• Good communication and teamwork skills: able to communicate effectively with team members and collaborate to complete project tasks.

职位名称：大语言模型实习生

康明斯数据科学和人工智能部正在寻求本科生或研究生的深入研究机会。这些机会会涵盖大语言模型在汽车和工业等垂直领域的应用探索和实践。

工作概要：

• 探索大语言模型在汽车和工业领域的应用场景

• 设计和开发垂直领域的大语言模型框架

• 构建和优化基于大语言模型的应用系统

• 评估和分析大语言模型在垂直领域下的应用效果

主要职责：

• 收集和整理领域数据: 整理汽车/工业领域相关的文本、代码、数据等，并进行清洗、标注和整理，为大语言模型的训练和应用提供高质量的数据基础

• 设计和实现大语言模型的应用方案: 根据具体应用场景，设计和实现基于大语言模型的解决方案，例如智能客服系统、自动问答系统、故障诊断系统等

• 开发和优化大语言模型的训练和推理流程: 优化大语言模型的训练和推理流程，提高模型的效率、准确性和可解释性

• 评估和分析大语言模型的应用效果: 对大语言模型在汽车和工业领域的应用效果进行评估和分析，并根据结果进行改进和优化

• 撰写技术文档和报告: 撰写关于大语言模型在汽车和工业领域的应用研究和开发的文档和报告，记录工作成果和经验教训。

• 在整个实习期间和实习结束后，向团队成员和利益相关者展示令人信服的、经过验证的故事

资格和能力：

• 计算机科学/数据科学/人工智能或相关专业本科或研究生在读: 具备扎实的计算机科学基础知识，熟悉数据结构、算法、编程语言等

• 熟悉自然语言处理 (NLP) 相关技术: 了解 NLP 的基本概念，例如词嵌入、语言模型、文本分类、机器翻译等

• 熟悉大语言模型 (LLM) 的相关技术: 了解 LLM 的基本概念和应用框架，例如 Transformer 、预训练模型、提示工程、检索增强生成、微调、LangChain等；

• 对主流开源大语言模型有过部署实践经历，例如ChatGLM，Llama等

• 有相关项目经验: 参与过 NLP / LLM 相关的项目开发，例如聊天机器人、文本生成、问答系统等

• 熟悉 Python 或其他编程语言: 能够熟练使用 Python 或其他编程语言进行代码编写和开发

• 良好的学习能力和解决问题的能力: 能够快速学习新知识和技术，并能够独立解决问题

• 良好的沟通能力和团队合作能力: 能够与团队成员有效沟通，并协作完成项目任务

Job Engineering

Organization Cummins Inc.

Role Category Hybrid

Job Type Student - Internship

ReqID 2402462

Relocation Package No