ModelBest

AI 研发工程师(大模型应用)

ModelBest  •  Onsite  •  14 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

AI 研发工程师(大模型应用)

北京、上海、深圳

社招

全职

技术 - 开发

职位 ID:A07072

职位描述

  1. 负责大模型应用、智能体和行业 AI 平台的核心模块设计与研发,包括任务规划、任务拆解、工作流编排、工具调用、记忆、反思和结果验证。 2. 建设模型接入与调用能力,支持同步和流式输出、模型路由、上下文管理、失败重试、降级、限流、超时控制及调用链路追踪。 3. 负责 RAG 相关能力建设,包括文档解析、切分、Embedding、向量检索、Rerank、证据引用和知识库更新。 使用 Python、Go 等技术栈,建设高可用服务、异步任务、消息队列、数据库及模型网关,保障系统稳定性和可维护性。 4. 协同算法团队完成 MiniCPM 及其他模型的服务化封装、性能优化与领域优化,参与 vLLM、SGLang、llama.cpp 或国产芯片推理栈的部署适配。 5. 参与 Docker、Kubernetes、CI/CD、监控、日志、告警和私有化离线安装能力建设,支持客户现场问题定位,并将真实业务需求沉淀为可复用的系统能力。

职位要求

  1. 本科及以上学历,计算机、软件工程、人工智能等相关专业优先。 2. 具备扎实的 Python 或 Go 开发能力,熟悉服务端开发、API 设计、数据库和常用中间件。 3. 理解大模型、RAG、Agent 的基本工作方式,至少在其中一个方向有实际项目经验。 4. 熟悉 FastAPI、PostgreSQL/MySQL、Redis、消息队列、Milvus 或其他向量数据库中的部分技术栈。 5. 具备良好的工程习惯,重视自动化测试、日志追踪、故障排查和版本管理,愿意处理从开发、联调到生产运行的完整问题。 加分项 1. 有智能体平台、数字员工、MCP、工具调用、多 Agent 协作或长任务执行经验。 2. 有 vLLM、SGLang、TensorRT-LLM、llama.cpp 或其他国产芯片适配经验。 3. 有端侧、边缘侧、离线环境、信创环境或一体机交付经验。

投递

ModelBest

About ModelBest

ModelBest established in August 2022, is an Artificial Intelligence technology company headquartered in Beijing, China. The company is deeply rooted in the field of general AI, with a focus on the innovation and application transformation of large-scale models. ModelBest boasts a prestigious founding R&D team from the Tsinghua in the AI field. Leveraging numerous cutting-edge technologies in natural language processing, the company is currently constructing a large-scale pre-trained model library and corresponding tools, aiming to standardize the technology and applications of large models.

Based on the capabilities of the CPM series of large models, ModelBest has successfully facilitated the intelligent upgrade and efficiency enhancement of various industries. Moreover, the company has released a multi-modal dialog assistant with hundreds of billions of parameters, “Luca", to the public. Adhering to the core philosophy of "intelligence encompassing all", we look forward to exploring and expanding unknown possibilities with global partners, aiming to ensure AI technology serves humanity for a better life in a safe and inclusive manner, laying a solid foundation for the advent of the AGI world.

OpenBMB (Open Lab for Big Model Base,https://github.com/OpenBMB), founded by ModelBest Inc & TsinghuaNLP, aims to build foundation models and systems towards AGI.

Industry
Biotech & Life Sciences
Company Size
11-50 employees
Headquarters
Beijing, CN
Year Founded
2022
Social Media