更新于 5月25日
职位描述
大模型算法深度学习机器学习自然语言处理Python计算机软件
python,Java,RAG， Prompt engineering,AI/LLM
Role Overview
As an AI Application Engineer, you’ll be responsible for integrating, fine-tuning, and operationalizing large language models and other AI components into production-grade software systems. This role focuses on post-training workflows—such as fine-tuning, prompt engineering, retrieval-augmented generation (RAG), vector database integration, and model deployment—rather than foundational model development.
You’ll work closely with backend engineers, product teams, and data teams to build intelligent apps that are fast, accurate, consistent and production-ready.
Key Responsibilities
- Integrate LLMs and other AI components into web and backend applications.
- Fine-tune open models using techniques like LoRA, QLoRA, or supervised fine-tuning.
- Build RAG pipelines using vector databases.
- Design and optimize prompts for various tasks (prompt chaining, templating, few-shot setups).
- Package and deploy models for inference
- Evaluate and monitor AI model performance in live environments.
- Ensure scalable, secure, and compliant use of AI systems in production.
- Stay informed on LLM tooling ecosystems (LangChain, LlamaIndex, OpenAI APIs, Hugging Face, Spring AI etc.)
Required Qualifications
- Bachelor’s or Master’s in Computer Science, Engineering, or a related field.
- 2+ years of experience building AI-augmented applications or services.
- Proficient in Python and familiar with frameworks like LangChain, Transformers, or Hugging Face datasets.
- Understanding of vector embeddings and experience with vector search tools.
- Strong grasp of model deployment workflows (e.g., Docker, REST APIs, cloud services like AWS/Microsoft Azure).
- Familiarity with prompt engineering strategies and LLM behavior tuning.
- Experience integrating with APIs from OpenAI, Anthropic, or open-source models like Mistral or LLaMA.
Preferred Qualifications
- Experience fine-tuning models using PEFT methods (LoRA/QLoRA).
- Familiarity with LLMOps, observability, and model evaluation
- Exposure to security, privacy, and responsible AI practices.
- Prior experience building chatbots, copilots, document analyzers, or other AI apps.
- Contributions to open-source AI tools or GenAI workflows.
As an AI Application Engineer, you’ll be responsible for integrating, fine-tuning, and operationalizing large language models and other AI components into production-grade software systems. This role focuses on post-training workflows—such as fine-tuning, prompt engineering, retrieval-augmented generation (RAG), vector database integration, and model deployment—rather than foundational model development.
You’ll work closely with backend engineers, product teams, and data teams to build intelligent apps that are fast, accurate, consistent and production-ready.
Key Responsibilities
- Integrate LLMs and other AI components into web and backend applications.
- Fine-tune open models using techniques like LoRA, QLoRA, or supervised fine-tuning.
- Build RAG pipelines using vector databases.
- Design and optimize prompts for various tasks (prompt chaining, templating, few-shot setups).
- Package and deploy models for inference
- Evaluate and monitor AI model performance in live environments.
- Ensure scalable, secure, and compliant use of AI systems in production.
- Stay informed on LLM tooling ecosystems (LangChain, LlamaIndex, OpenAI APIs, Hugging Face, Spring AI etc.)
Required Qualifications
- Bachelor’s or Master’s in Computer Science, Engineering, or a related field.
- 2+ years of experience building AI-augmented applications or services.
- Proficient in Python and familiar with frameworks like LangChain, Transformers, or Hugging Face datasets.
- Understanding of vector embeddings and experience with vector search tools.
- Strong grasp of model deployment workflows (e.g., Docker, REST APIs, cloud services like AWS/Microsoft Azure).
- Familiarity with prompt engineering strategies and LLM behavior tuning.
- Experience integrating with APIs from OpenAI, Anthropic, or open-source models like Mistral or LLaMA.
Preferred Qualifications
- Experience fine-tuning models using PEFT methods (LoRA/QLoRA).
- Familiarity with LLMOps, observability, and model evaluation
- Exposure to security, privacy, and responsible AI practices.
- Prior experience building chatbots, copilots, document analyzers, or other AI apps.
- Contributions to open-source AI tools or GenAI workflows.
工作地点
天津滨海新区渣打环球商业服务有限公司
公司信息
公司介绍
凯捷(Capgemini)是一家由AI驱动的全球业务与技术转型合作伙伴，旨在创造切实的商业价值。我们为企业构想未来，并通过A1、技术和人才将其变为现实。凯捷是一个负责任的多元化组织，集团成立于1967年，总部位于法国巴黎，在50多个国家拥有近42万名团队成员。我们凭借深厚的行业专业知识和强大的合作伙伴生态系统，提供端到端的服务和解决方案，充分发挥战略、技术、设计、工程及业务运营等方面的能力。集团2024年全球收入达到221亿欧元。对每一位入职的员工保证福利，六险一金，十三薪，试用期全额薪资，超长福利假期，12天带薪病假，欢迎各位加入凯捷。
工商信息
企业名称 凯捷咨询（中国）有限公司
企业类型 有限责任公司（外国法人独资）
法人代表 OLAF PIETSCHNER
经营状态 存续
成立时间 1997-10-28
注册资本 9181.22万美元
认证资质
营业执照信息
